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

    Neuronpedia

    INDEX
    Explanations

    maximum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     все
    -0.07
     亚
    -0.06
     Main
    -0.06
    拓
    -0.06
     clues
    -0.06
     bulunan
    -0.06
     Luke
    -0.06
    -like
    -0.06
     STANDARD
    -0.06
     Gar
    -0.06
    POSITIVE LOGITS
    )o
    0.07
    계획
    0.07
    -stat
    0.07
    ]--;↵
    0.07
    ,False
    0.06
     Phó
    0.06
    _pot
    0.06
    Sigma
    0.06
    ادية
    0.06
    .......
    0.06
    Act Density 0.017%

    No Known Activations