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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.86
     Signalez
    -0.85
    SharedDtor
    -0.84
    хьтан
    -0.84
     unknownFields
    -0.83
     kaarangay
    -0.82
    InitVars
    -0.81
    LookAnd
    -0.80
    ftagPool
    -0.80
    principalTable
    -0.79
    POSITIVE LOGITS
     varandra
    0.28
     évent
    0.27
     récentes
    0.27
     récents
    0.24
     démission
    0.23
     cuáles
    0.23
     découver
    0.23
     rêves
    0.22
     keskus
    0.22
     dépla
    0.22
    Act Density 0.001%

    No Known Activations