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

    Neuronpedia

    INDEX
    Explanations

    jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     campaigned
    -0.07
     pressures
    -0.07
     polygon
    -0.07
    灵
    -0.06
    dyž
    -0.06
     визнача
    -0.06
    981
    -0.06
     postponed
    -0.06
    ové
    -0.06
     dr
    -0.06
    POSITIVE LOGITS
    _batch
    0.07
    (pointer
    0.06
     Gre
    0.06
     mixin
    0.06
     lacked
    0.06
    (errorMessage
    0.06
     şiddet
    0.06
    らない
    0.06
    АТ
    0.06
    Dual
    0.06
    Act Density 0.013%

    No Known Activations