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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '#
    -0.07
     timed
    -0.07
     turns
    -0.06
    (symbol
    -0.06
    алю
    -0.06
     曰
    -0.06
    <<<<
    -0.06
    _Draw
    -0.06
     statements
    -0.06
     선
    -0.06
    POSITIVE LOGITS
    shell
    0.08
    =M
    0.07
    icultural
    0.07
    GRP
    0.06
     YM
    0.06
    .inverse
    0.06
    _mul
    0.06
     america
    0.06
    Foot
    0.06
    (Channel
    0.06
    Act Density 0.041%

    No Known Activations