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

    Neuronpedia

    INDEX
    Explanations

    Code reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AppState
    -0.06
    必不可
    -0.06
    ﱪ
    -0.06
    Sure
    -0.06
     editorial
    -0.06
    anson
    -0.06
     npm
    -0.06
     Jeff
    -0.06
     Joshua
    -0.06
     insurers
    -0.06
    POSITIVE LOGITS
    _create
    0.09
    .....↵↵
    0.08
    datable
    0.08
     인간
    0.07
    YSTICK
    0.07
    גובות
    0.07
    ::↵↵
    0.07
     hydrated
    0.07
    .Create
    0.07
    逆
    0.07
    Act Density 0.018%

    No Known Activations