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

    Neuronpedia

    INDEX
    Explanations

    programming, math, languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parents
    -0.08
     pumpkin
    -0.08
    .sigmoid
    -0.08
     Olympus
    -0.07
     predictable
    -0.07
     junge
    -0.07
     graduated
    -0.07
     interchangeable
    -0.07
     wee
    -0.07
     beau
    -0.07
    POSITIVE LOGITS
    League
    0.07
    类似
    0.07
    博文
    0.07
    חופ
    0.06
    富含
    0.06
    �
    0.06
    europ
    0.06
    有关
    0.06
    حساب
    0.06
     jav
    0.06
    Act Density 0.000%

    No Known Activations