Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terminology and formal expressions in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    entry linked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paravant
    -0.53
     nuage
    -0.50
     isInitialized
    -0.46
     couvercle
    -0.43
     يتيمه
    -0.42
    outchouc
    -0.41
     jouet
    -0.41
    bootstrapcdn
    -0.40
     rocher
    -0.40
     tolerances
    -0.40
    POSITIVE LOGITS
    новништво
    0.64
     Италијани
    0.59
    NameInMap
    0.50
    \{\\
    0.49
    TypedDataSet
    0.48
     ligiloj
    0.43
     endblock
    0.43
    ativement
    0.43
     StringField
    0.42
    Vidite
    0.42
    Act Density 0.222%

    No Known Activations