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

    Neuronpedia

    INDEX
    Explanations

    users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     السعود
    -0.07
    ılıp
    -0.06
    apters
    -0.06
    ])**
    -0.06
    _lv
    -0.06
    meler
    -0.06
     pang
    -0.06
    _avatar
    -0.06
    getClientOriginal
    -0.06
     Weird
    -0.06
    POSITIVE LOGITS
    massage
    0.07
     clim
    0.07
     slap
    0.07
    .А
    0.06
     ближ
    0.06
    Tim
    0.06
     romance
    0.06
     civilians
    0.06
     silence
    0.06
     sich
    0.06
    Act Density 0.000%

    No Known Activations