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

    Neuronpedia

    INDEX
    Explanations

    configure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ccion
    -0.07
     joint
    -0.07
     hitting
    -0.07
     overlapping
    -0.07
    ashed
    -0.07
    部分内容
    -0.07
     setOpen
    -0.07
    _predicted
    -0.06
    ɔ
    -0.06
    消
    -0.06
    POSITIVE LOGITS
    察看
    0.07
    >>>(
    0.07
    훠
    0.07
     escal
    0.07
     aden
    0.07
     persuade
    0.07
    宅
    0.06
        
    0.06
     حو
    0.06
     tüm
    0.06
    Act Density 0.002%

    No Known Activations