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

    Neuronpedia

    INDEX
    Explanations

    various metrics related to accuracy and performance evaluations

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

    quantifying states and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.77
    DeleteBehavior
    -0.69
    DockStyle
    -0.62
    Personensuche
    -0.61
     OMITBAD
    -0.59
    :✨
    -0.56
    CGRectMake
    -0.56
     wireType
    -0.55
    principalColumn
    -0.55
    MessageTagHelper
    -0.52
    POSITIVE LOGITS
    nonatomic
    0.31
     insectes
    0.29
    ability
    0.29
    irability
    0.29
     humains
    0.29
     elé
    0.29
     Stimmung
    0.29
    piecze
    0.28
     interesse
    0.28
    Sco
    0.28
    Act Density 0.325%

    No Known Activations