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

    Neuronpedia

    INDEX
    Explanations

    services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enjoyable
    -0.07
     }}</
    -0.07
     getenv
    -0.06
    .readFile
    -0.06
    芬
    -0.06
    _the
    -0.06
     производства
    -0.06
     defenseman
    -0.06
    -effective
    -0.06
    .En
    -0.06
    POSITIVE LOGITS
     ncols
    0.07
     باد
    0.07
     silence
    0.07
     nick
    0.06
    .bias
    0.06
    Unless
    0.06
     PARTIC
    0.06
    操
    0.06
    iners
    0.06
     měst
    0.06
    Act Density 0.014%

    No Known Activations