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

    Neuronpedia

    INDEX
    Explanations

    Random characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تامبر
    -0.07
     jej
    -0.07
     svm
    -0.07
     treasures
    -0.06
    brtc
    -0.06
     Sunder
    -0.06
    aad
    -0.06
     čas
    -0.06
    하지만
    -0.06
     جشن
    -0.06
    POSITIVE LOGITS
    ίο
    0.07
    Г
    0.07
    REATE
    0.06
    @GeneratedValue
    0.06
    implified
    0.06
    Κ
    0.06
    pine
    0.06
    ARGV
    0.06
    خط
    0.06
     TestBed
    0.06
    Act Density 0.065%

    No Known Activations