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

    Neuronpedia

    INDEX
    Explanations

    Attributions to sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	git
    -0.08
     три
    -0.07
    周期
    -0.06
    _CELL
    -0.06
    视
    -0.06
     setData
    -0.06
     soar
    -0.06
     Тут
    -0.06
     waive
    -0.06
    _SY
    -0.06
    POSITIVE LOGITS
     Forbidden
    0.07
     asympt
    0.07
     pissed
    0.07
    licher
    0.06
    ificacion
    0.06
     Decom
    0.06
     deserted
    0.06
    .Undef
    0.06
     "",↵
    0.06
    jen
    0.06
    Act Density 0.034%

    No Known Activations