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

    Neuronpedia

    INDEX
    Explanations

    degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    on
    -0.08
    一心
    -0.08
     addTarget
    -0.07
     VN
    -0.07
    _List
    -0.07
    ٱ
    -0.07
    bidden
    -0.07
     liken
    -0.07
    SENT
    -0.06
    心中的
    -0.06
    POSITIVE LOGITS
     degree
    0.09
     degrees
    0.08
    krę
    0.08
     Degrees
    0.08
    垡
    0.07
    יטה
    0.07
     stairs
    0.07
    קלא
    0.07
    0.07
    격
    0.07
    Act Density 0.022%

    No Known Activations