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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    垕
    -0.06
    .Amount
    -0.06
    溃
    -0.06
    tdown
    -0.06
    缱
    -0.06
     sł
    -0.06
    אוטומ
    -0.06
    leared
    -0.06
    ➸
    -0.06
    gorm
    -0.06
    POSITIVE LOGITS
     Shadows
    0.07
    яв
    0.07
    .ActionBar
    0.07
    蕉
    0.07
     lesbian
    0.06
     Rosie
    0.06
    戟
    0.06
    กระจาย
    0.06
     probably
    0.06
    阴影
    0.06
    Act Density 0.012%

    No Known Activations