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

    Neuronpedia

    INDEX
    Explanations

    src

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cages
    -0.07
    vas
    -0.07
     çözüm
    -0.07
    hiba
    -0.06
     womb
    -0.06
     دم
    -0.06
     길
    -0.06
     рей
    -0.06
    ipples
    -0.06
    remen
    -0.05
    POSITIVE LOGITS
    ingt
    0.07
    Monad
    0.07
    ividual
    0.07
    gether
    0.07
     Shaun
    0.07
     başlayan
    0.06
     Monad
    0.06
    ज़
    0.06
    П
    0.06
    olic
    0.06
    Act Density 0.004%

    No Known Activations