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

    Neuronpedia

    INDEX
    Explanations

    household demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vání
    -0.07
    습니다
    -0.07
    っぱ
    -0.07
    kte
    -0.06
    emb
    -0.06
    estimate
    -0.06
    rete
    -0.06
    .neighbors
    -0.06
    jištění
    -0.06
    řad
    -0.06
    POSITIVE LOGITS
     Lesbian
    0.08
    ZN
    0.06
     supporting
    0.06
     друго
    0.06
    eresa
    0.06
    "));↵↵
    0.06
    estination
    0.06
    _tick
    0.06
     bumper
    0.06
     jiného
    0.06
    Act Density 0.001%

    No Known Activations