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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate research studies or findings

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

    article entitled or covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Glaube
    -0.31
    endosi
    -0.30
    Bretagne
    -0.30
     Nouvelle
    -0.28
     kommit
    -0.28
     sagesse
    -0.28
     ayer
    -0.28
     Töchter
    -0.27
    ApiModelProperty
    -0.27
    üsseldorf
    -0.26
    POSITIVE LOGITS
    BeginContext
    0.69
    parsedMessage
    0.65
    AnchorStyles
    0.63
    \{\\
    0.60
    findpost
    0.60
    ISupport
    0.59
    LEncoder
    0.59
    AxisAlignment
    0.59
    enumi
    0.58
    DockStyle
    0.57
    Act Density 0.398%

    No Known Activations