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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulae

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grows
    -0.08
    .box
    -0.06
    _supp
    -0.06
    370
    -0.06
    -main
    -0.06
     Youtube
    -0.06
     Concent
    -0.06
     Milk
    -0.06
     язы
    -0.06
     usu
    -0.06
    POSITIVE LOGITS
    エ
    0.07
    .DisplayMember
    0.06
     socialist
    0.06
     Loop
    0.06
    _CHOICES
    0.06
     contradiction
    0.06
    Insensitive
    0.06
    [T
    0.06
     говорит
    0.06
     gec
    0.06
    Act Density 0.027%

    No Known Activations