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

    Neuronpedia

    INDEX
    Explanations

    software documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    けない
    -0.06
    amientos
    -0.06
    $k
    -0.06
    928
    -0.06
    692
    -0.06
    uples
    -0.06
     negotiation
    -0.06
     Joyce
    -0.06
    veloper
    -0.06
    uren
    -0.05
    POSITIVE LOGITS
     magnet
    0.07
     Rate
    0.07
    (Api
    0.07
     RandomForest
    0.07
    _cat
    0.07
    ेटर
    0.06
     massa
    0.06
     Pete
    0.06
    .speed
    0.06
    _RECEIVED
    0.06
    Act Density 0.044%

    No Known Activations