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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Род
    -0.07
    よりも
    -0.07
     OTHER
    -0.06
     Manor
    -0.06
    their
    -0.06
    민국
    -0.06
    decl
    -0.06
     myth
    -0.06
     mour
    -0.06
    亭
    -0.06
    POSITIVE LOGITS
    �
    0.06
    CAF
    0.06
     cheesy
    0.06
    cap
    0.06
    _cfg
    0.06
    Environmental
    0.06
    اضي
    0.06
    面积
    0.06
    dag
    0.06
    _ctrl
    0.06
    Act Density 0.002%

    No Known Activations