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

    Neuronpedia

    INDEX
    Explanations

    juror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ène
    -0.07
     parm
    -0.07
    izin
    -0.07
     sinks
    -0.06
     bezpečnost
    -0.06
     lên
    -0.06
     دون
    -0.06
    825
    -0.06
     brib
    -0.06
    μβρίου
    -0.06
    POSITIVE LOGITS
    eneral
    0.06
    _Valid
    0.06
    lid
    0.06
    	GL
    0.06
     jurors
    0.06
    Ryan
    0.06
    ?('
    0.06
    中学
    0.06
     太
    0.06
     gauss
    0.06
    Act Density 0.001%

    No Known Activations