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

    Neuronpedia

    INDEX
    Explanations

    assignment statements in code

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

    programming code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.79
     насељу
    -0.72
    MLLoader
    -0.70
    offsetof
    -0.68
    principalTable
    -0.65
     Савезне
    -0.63
     autorytatywna
    -0.62
    нгред
    -0.62
    httphttps
    -0.62
     Wikispecies
    -0.62
    POSITIVE LOGITS
    anmoins
    0.29
    bezpe
    0.28
     concreto
    0.28
     chodzi
    0.27
     perak
    0.27
     horaires
    0.27
     oficina
    0.26
     resultat
    0.26
     pouce
    0.26
     silikon
    0.25
    Act Density 0.048%

    No Known Activations