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

    Neuronpedia

    INDEX
    Explanations

    input output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (guess
    -0.06
    undle
    -0.06
    _publisher
    -0.06
    iego
    -0.06
    ensen
    -0.06
     (){↵
    -0.06
     Deutschland
    -0.06
     nos
    -0.06
    .internal
    -0.06
    _stage
    -0.06
    POSITIVE LOGITS
     Chili
    0.07
     permalink
    0.07
    .GetChild
    0.07
     Mash
    0.06
     Irvine
    0.06
    /"+
    0.06
    _Parameter
    0.06
    chester
    0.06
    _HEIGHT
    0.06
    _mB
    0.06
    Act Density 0.004%

    No Known Activations