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

    Neuronpedia

    INDEX
    Explanations

    rules and goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     갤로그로
    -0.07
     бак
    -0.06
    _qos
    -0.06
    .rgb
    -0.06
    webkit
    -0.06
    queueReusable
    -0.06
    ___
    -0.06
     Photos
    -0.06
     Fond
    -0.06
    DSL
    -0.06
    POSITIVE LOGITS
     Too
    0.07
     SIGN
    0.07
     العن
    0.07
    ักษณะ
    0.06
    ！↵↵
    0.06
    FFFFFFFF
    0.06
     strcat
    0.06
     Exposure
    0.06
     Cooler
    0.06
     Nome
    0.06
    Act Density 0.043%

    No Known Activations