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

    Neuronpedia

    INDEX
    Explanations

    US government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wir
    -0.07
    Alpha
    -0.07
    ouri
    -0.06
    Util
    -0.06
    )+(
    -0.06
    .Objects
    -0.06
    -rule
    -0.06
    По
    -0.06
    920
    -0.06
    Summary
    -0.06
    POSITIVE LOGITS
    osloven
    0.06
     NK
    0.06
     Insp
    0.06
     검
    0.06
     надеж
    0.06
     drank
    0.06
    /scripts
    0.06
     complic
    0.06
    initely
    0.06
    brero
    0.06
    Act Density 0.006%

    No Known Activations