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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不断增加
    -0.08
    PG
    -0.07
     inspection
    -0.07
     kite
    -0.07
    �
    -0.07
    [\
    -0.07
    upil
    -0.07
     insightful
    -0.07
     lion
    -0.06
    [ch
    -0.06
    POSITIVE LOGITS
    Ę
    0.07
    ước
    0.07
    Ordered
    0.07
    íses
    0.07
    нии
    0.07
     como
    0.07
    scenes
    0.07
     אליה
    0.07
    _BODY
    0.06
     {}),↵
    0.06
    Act Density 0.064%

    No Known Activations