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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extrav
    -0.07
     BANK
    -0.07
    Chess
    -0.06
     BORDER
    -0.06
     intimacy
    -0.06
     ราย
    -0.06
     Petty
    -0.06
    κρι
    -0.06
    öffent
    -0.06
    ีข
    -0.06
    POSITIVE LOGITS
    =M
    0.07
    附近
    0.07
     Health
    0.07
    镜
    0.06
    чих
    0.06
    ?
    0.06
     skoro
    0.06
     cocina
    0.06
     Marshal
    0.06
    >↵
    0.06
    Act Density 0.000%

    No Known Activations