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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اهش
    -0.07
    (cos
    -0.07
    标题
    -0.06
     yanı
    -0.06
     negative
    -0.06
    ОН
    -0.06
     disrupting
    -0.06
    _Edit
    -0.06
     corridor
    -0.06
     hopefully
    -0.06
    POSITIVE LOGITS
    Barrier
    0.08
     масла
    0.07
    	TArray
    0.07
    -term
    0.07
    utowired
    0.06
     sincerely
    0.06
    _REFERER
    0.06
     Gay
    0.06
    <Any
    0.06
     turbulent
    0.06
    Act Density 0.000%

    No Known Activations