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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toll
    -0.07
    .ToLower
    -0.06
     Axis
    -0.06
    拿
    -0.06
     dveře
    -0.06
    _ro
    -0.06
     moot
    -0.06
    _PIX
    -0.06
    ähr
    -0.06
    663
    -0.06
    POSITIVE LOGITS
    //---------------------------------------------------------------------------↵↵
    0.07
     organising
    0.06
    features
    0.06
    .intValue
    0.06
    SearchParams
    0.06
     Elizabeth
    0.06
     Corporate
    0.06
    -eff
    0.06
    اك
    0.06
    ->{_
    0.06
    Act Density 0.008%

    No Known Activations