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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    _malloc
    -0.06
    (tol
    -0.06
    :X
    -0.06
     redirect
    -0.06
     readdir
    -0.06
    arakter
    -0.06
     kotlinx
    -0.06
     �
    -0.06
     barric
    -0.06
    POSITIVE LOGITS
    сь
    0.07
     Apr
    0.06
    Chess
    0.06
     الأس
    0.06
    ['__
    0.06
    .responses
    0.06
     Chemical
    0.06
    رة
    0.06
     가
    0.06
     克
    0.06
    Act Density 0.920%

    No Known Activations