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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scientific measurements and experimental outcomes

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

    results, properties, and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.63
    ENDIAN
    -0.47
    OGND
    -0.47
    ÓS
    -0.44
    ELTS
    -0.44
     età
    -0.44
    fjspx
    -0.43
    Bakgrunnsstoff
    -0.43
     Савезне
    -0.43
     ModelExpression
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.45
    Artículo
    0.44
    addComponent
    0.44
    Synonym
    0.43
    awtextra
    0.42
     statistic
    0.42
    steroid
    0.41
     Jüng
    0.40
    Задача
    0.40
    httphttps
    0.40
    Act Density 1.206%

    No Known Activations