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

    Neuronpedia

    INDEX
    Explanations

    elements related to understanding concepts and achieving goals

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

    before infinitives or pronouns

    np_acts-logits-general · gemini-2.0-flash

    infinitive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.58
    transQ
    -0.56
     Raise
    -0.50
    Raise
    -0.47
     Raising
    -0.46
    خول
    -0.44
    vade
    -0.43
     ProtoMessage
    -0.43
     zprá
    -0.42
    COW
    -0.42
    POSITIVE LOGITS
     memili
    0.76
    それを
    0.75
     it
    0.74
    把它
    0.72
     niitä
    0.65
     оно
    0.65
     그것
    0.64
     nó
    0.61
    MethodManager
    0.61
     Administrativna
    0.59
    Act Density 0.487%

    No Known Activations