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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ax
    -0.07
    ienza
    -0.06
     나가
    -0.06
    /Images
    -0.06
    (where
    -0.06
    _AND
    -0.06
     元
    -0.06
    Ax
    -0.06
    (equal
    -0.06
    하시
    -0.06
    POSITIVE LOGITS
    
    0.07
     exit
    0.07
    _COORD
    0.07
     معدن
    0.06
     interstate
    0.06
     rv
    0.06
     statistic
    0.06
     autom
    0.06
    _CALL
    0.06
     اعتر
    0.06
    Act Density 0.015%

    No Known Activations