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

    Neuronpedia

    INDEX
    Explanations

    Chemical experiment descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝓋
    -0.08
    熜
    -0.07
    纯洁
    -0.07
    恶魔
    -0.07
    🍧
    -0.07
     Sylvia
    -0.07
    _IMETHOD
    -0.07
    𝕁
    -0.07
    formerly
    -0.07
    umptech
    -0.06
    POSITIVE LOGITS
    Le
    0.07
     CON
    0.07
    dl
    0.07
    ements
    0.06
    step
    0.06
    부
    0.06
    tes
    0.06
     branch
    0.06
     genders
    0.06
     Speaker
    0.06
    Act Density 0.037%

    No Known Activations