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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     см
    -0.07
     Plan
    -0.07
     riv
    -0.06
     Cunning
    -0.06
    Від
    -0.06
    —in
    -0.06
    .za
    -0.06
     feet
    -0.06
    ده
    -0.06
    \"
    -0.06
    POSITIVE LOGITS
     Turing
    0.07
     youngster
    0.06
     leaderboard
    0.06
     Ord
    0.06
     самостоятель
    0.06
    veřej
    0.06
    CLR
    0.06
     dependency
    0.06
    )init
    0.06
    .Scope
    0.06
    Act Density 0.020%

    No Known Activations