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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCH
    -0.07
    bus
    -0.06
    าษ
    -0.06
     Lawrence
    -0.06
    (()
    -0.06
     abilities
    -0.06
    pton
    -0.06
    .workflow
    -0.06
     ucfirst
    -0.06
    /">
    -0.06
    POSITIVE LOGITS
    861
    0.08
    741
    0.07
    โลก
    0.07
    好的
    0.07
     العرب
    0.07
    控制
    0.07
    880
    0.07
     編
    0.06
     `(
    0.06
    670
    0.06
    Act Density 0.000%

    No Known Activations