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

    Neuronpedia

    INDEX
    Explanations

    knowledge and understanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reb
    -0.07
    rotation
    -0.07
    _validation
    -0.07
    ęk
    -0.07
    padding
    -0.07
    银行
    -0.06
     maxX
    -0.06
     palace
    -0.06
     entra
    -0.06
    unan
    -0.06
    POSITIVE LOGITS
    (ff
    0.07
    ']=$
    0.06
     utilizing
    0.06
    -know
    0.06
    _STAR
    0.06
    []=$
    0.06
    提高
    0.06
    �i
    0.06
    ือข
    0.06
    اصيل
    0.06
    Act Density 0.049%

    No Known Activations