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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities

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

    code response handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.56
    ollectionView
    -0.54
     desmotivaciones
    -0.52
    ParallelGroup
    -0.49
    AndEndTag
    -0.48
     Geſch
    -0.47
     sauvegarde
    -0.47
     Italij
    -0.47
    CGRectMake
    -0.46
     tempel
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.57
    complexContent
    0.53
    internalType
    0.43
    stdbool
    0.41
    something
    0.40
     ++;
    0.38
    GenerationType
    0.38
     comigo
    0.38
     iirc
    0.37
    ++;
    0.37
    Act Density 0.151%

    No Known Activations