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
    .Created
    -0.07
    육
    -0.07
    oscope
    -0.07
    Div
    -0.07
    Jud
    -0.06
    ustralia
    -0.06
    TRA
    -0.06
    rchive
    -0.06
    itated
    -0.06
    .OR
    -0.06
    POSITIVE LOGITS
     segmented
    0.07
     stake
    0.07
    .addButton
    0.07
    Rendering
    0.06
     fibonacci
    0.06
     susceptible
    0.06
     congest
    0.06
     ισχ
    0.06
     cậu
    0.06
    权限
    0.06
    Act Density 0.011%

    No Known Activations