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

    Neuronpedia

    INDEX
    Explanations

    charset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('--
    -0.07
     fayd
    -0.07
    @AllArgsConstructor
    -0.06
    Editor
    -0.06
     Often
    -0.06
    ngo
    -0.06
    ところ
    -0.06
     Sund
    -0.06
    .addView
    -0.06
    ідно
    -0.06
    POSITIVE LOGITS
     charset
    0.09
    "You
    0.07
     pseudo
    0.07
     rear
    0.07
    .channels
    0.06
    Charsets
    0.06
    requent
    0.06
    auté
    0.06
    aleb
    0.06
    	K
    0.06
    Act Density 0.001%

    No Known Activations