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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    included
    -0.06
    ौ
    -0.06
    .sourceforge
    -0.06
    ,"%
    -0.06
     Edge
    -0.06
    나
    -0.06
    ülü
    -0.06
    cdr
    -0.06
    yny
    -0.06
    +'/'+
    -0.06
    POSITIVE LOGITS
     MICRO
    0.08
     costume
    0.06
    _pago
    0.06
    claims
    0.06
     architectures
    0.06
     Tas
    0.06
     puppet
    0.06
    選手
    0.06
    .AspNetCore
    0.06
     selbst
    0.06
    Act Density 0.124%

    No Known Activations