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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     İs
    -0.07
    wnd
    -0.07
     constit
    -0.07
    拤
    -0.07
    溏
    -0.07
    ético
    -0.06
    คอน
    -0.06
     carrots
    -0.06
     GetById
    -0.06
    POSITIVE LOGITS
    曾
    0.07
     BYTE
    0.07
    (sqrt
    0.07
    被执行
    0.07
     (?
    0.07
    不久前
    0.07
    ificant
    0.06
    Fragment
    0.06
     Zuk
    0.06
    =utf
    0.06
    Act Density 0.089%

    No Known Activations