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

    Neuronpedia

    INDEX
    Explanations

    cough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    策
    -0.07
    Mirror
    -0.07
    ازم
    -0.06
     zařízení
    -0.06
    elight
    -0.06
     Seat
    -0.06
     Storage
    -0.06
     stars
    -0.06
    Encryption
    -0.06
     الذ
    -0.06
    POSITIVE LOGITS
     cough
    0.10
    νη
    0.07
    /mock
    0.07
    normally
    0.06
    ahkan
    0.06
     bathroom
    0.06
    tribute
    0.06
    temporary
    0.06
     Cummings
    0.06
    _SAMPL
    0.06
    Act Density 0.005%

    No Known Activations