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

    Neuronpedia

    INDEX
    Explanations

    schemas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criptors
    -0.07
     cold
    -0.06
     Tower
    -0.06
     skull
    -0.06
    onitor
    -0.06
     turf
    -0.06
    voice
    -0.06
     PhD
    -0.06
     Independ
    -0.06
     cursor
    -0.06
    POSITIVE LOGITS
    (log
    0.07
    เลข
    0.07
     خطر
    0.06
    노출
    0.06
     işe
    0.06
     suất
    0.06
     bíl
    0.06
    違い
    0.06
    unal
    0.06
    इसक
    0.06
    Act Density 0.001%

    No Known Activations