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

    Neuronpedia

    INDEX
    Explanations

    born

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slots
    -0.06
    VICES
    -0.06
    Mo
    -0.06
     sliding
    -0.06
    疗
    -0.06
    џџџџџџџџ
    -0.06
    _xt
    -0.06
     ให
    -0.06
    상
    -0.06
    那样
    -0.06
    POSITIVE LOGITS
    .docs
    0.07
     differentiation
    0.07
     &,
    0.06
    operative
    0.06
     exhibits
    0.06
    generate
    0.06
    _VERSION
    0.06
     convertible
    0.06
    _reset
    0.06
     PSP
    0.06
    Act Density 0.003%

    No Known Activations