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

    Neuronpedia

    INDEX
    Explanations

    adverbs and their variations

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

    adverbs and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.53
     Meksiku
    -0.52
     houſe
    -0.45
     Infórmanos
    -0.44
     estadounid
    -0.44
     Houſe
    -0.44
     niedersachsen
    -0.43
    \{\\
    -0.41
     alamu
    -0.41
    httphttps
    -0.40
    POSITIVE LOGITS
    UTELY
    0.54
    ReusableCell
    0.49
    expandindo
    0.44
    ificantly
    0.44
    følgelig
    0.43
    vably
    0.42
     merely
    0.42
    oneg
    0.42
    MemoryWarning
    0.41
    AddTagHelper
    0.40
    Act Density 0.076%

    No Known Activations