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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wrapped
    -0.07
     XF
    -0.07
     GTA
    -0.07
     Bez
    -0.06
     Rafael
    -0.06
     causal
    -0.06
    _kernel
    -0.06
    裡
    -0.06
    .trim
    -0.06
    .MessageBox
    -0.06
    POSITIVE LOGITS
     çağ
    0.07
    .Font
    0.06
    ESP
    0.06
     THERE
    0.06
     seja
    0.06
    ці
    0.06
    .List
    0.06
     Policies
    0.06
     Coupons
    0.06
     ver
    0.06
    Act Density 0.000%

    No Known Activations