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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آنها
    -0.07
     kanı
    -0.07
     hob
    -0.06
     kanıt
    -0.06
    ması
    -0.06
    leyin
    -0.06
    ’deki
    -0.06
     البد
    -0.06
     lineage
    -0.06
    lında
    -0.06
    POSITIVE LOGITS
    getId
    0.07
     CERT
    0.07
    \admin
    0.06
    _ASSOC
    0.06
     fall
    0.06
    reet
    0.06
     european
    0.06
     buc
    0.06
     Yale
    0.06
    /b
    0.06
    Act Density 0.085%

    No Known Activations