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

    Neuronpedia

    INDEX
    Explanations

    Awards and nominations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    filtr
    -0.07
     Faith
    -0.07
    oard
    -0.07
    _quant
    -0.06
     dp
    -0.06
     Cave
    -0.06
    ailed
    -0.06
    .initialize
    -0.06
    argv
    -0.06
     chant
    -0.06
    POSITIVE LOGITS
     бит
    0.07
     Dietary
    0.07
     thậm
    0.06
    _REFERER
    0.06
    _traffic
    0.06
    internet
    0.06
    战斗
    0.06
    恨
    0.06
    にな
    0.06
     warped
    0.06
    Act Density 0.012%

    No Known Activations