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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    มาย
    -0.08
    wan
    -0.07
    Trust
    -0.06
    ataloader
    -0.06
     θεω
    -0.06
     Manson
    -0.06
    nama
    -0.06
     Porto
    -0.06
    宜
    -0.06
     Fun
    -0.06
    POSITIVE LOGITS
    FFFFFF
    0.07
    )])
    0.06
     eas
    0.06
    >",
    0.06
     Charlottesville
    0.06
    .Click
    0.06
    	className
    0.06
    ())),
    0.06
    摆
    0.06
    :</
    0.06
    Act Density 0.009%

    No Known Activations