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

    Neuronpedia

    INDEX
    Explanations

    expressions of motivation and responsibility towards positive actions and community support

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

    making a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MethodInfo
    -0.44
    complexType
    -0.44
    PMailer
    -0.42
    glMatrixMode
    -0.41
    inette
    -0.40
     hipó
    -0.40
    Билгалдахарш
    -0.39
    partimento
    -0.38
     threatening
    -0.38
     thicknesses
    -0.38
    POSITIVE LOGITS
    ArrowToggle
    0.50
    Cyfarwyddwr
    0.48
     CanadaChoose
    0.47
     saites
    0.46
     useAppContext
    0.46
     Administrativna
    0.46
    RTSC
    0.43
    новништво
    0.43
    tagHelperRunner
    0.43
     Keluarga
    0.43
    Act Density 0.016%

    No Known Activations