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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    احتمال
    -0.08
     advocate
    -0.07
    )):
    -0.07
    edb
    -0.06
    警示教育
    -0.06
    upro
    -0.06
    延长
    -0.06
    Todd
    -0.06
    alerts
    -0.06
    Tonight
    -0.06
    POSITIVE LOGITS
    AKE
    0.07
    OLE
    0.07
    undred
    0.07
     lac
    0.07
     사
    0.06
    Cou
    0.06
     Cadillac
    0.06
    错误
    0.06
    _algo
    0.06
     Cookies
    0.06
    Act Density 0.017%

    No Known Activations