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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToDo
    -0.07
    ढ
    -0.07
    .templates
    -0.06
     turbo
    -0.06
     dav
    -0.06
    _PLAYER
    -0.06
    .DELETE
    -0.06
    为空
    -0.06
     Har
    -0.06
     barn
    -0.06
    POSITIVE LOGITS
    .hm
    0.07
    .Step
    0.07
    (play
    0.07
     disappointment
    0.07
    itled
    0.07
    nesday
    0.07
    _green
    0.06
     shaping
    0.06
    (month
    0.06
    .prefix
    0.06
    Act Density 0.000%

    No Known Activations