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

    Neuronpedia

    INDEX
    Explanations

    Programming flags/parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خوب
    -0.06
     Minneapolis
    -0.06
    Qué
    -0.06
     infect
    -0.06
    CAT
    -0.06
     wł
    -0.06
     Lav
    -0.06
    pired
    -0.06
     успеш
    -0.06
    虚
    -0.06
    POSITIVE LOGITS
    ším
    0.07
     Conditional
    0.06
    .TR
    0.06
    anner
    0.06
     Feeling
    0.06
    ausal
    0.06
    ура
    0.06
    acic
    0.06
    _actor
    0.06
    áte
    0.06
    Act Density 0.017%

    No Known Activations