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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peaks
    -0.05
    Px
    -0.05
    /fl
    -0.05
     Hawkins
    -0.05
     vak
    -0.05
    sp
    -0.05
     şüph
    -0.05
    .top
    -0.05
     Known
    -0.05
    /ca
    -0.05
    POSITIVE LOGITS
     glyc
    0.08
    ModelIndex
    0.07
     CONS
    0.06
    (enemy
    0.06
    shelf
    0.06
    跳
    0.06
     QWidget
    0.06
    rolled
    0.06
     RHS
    0.06
    数据
    0.06
    Act Density 0.005%

    No Known Activations