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

    Neuronpedia

    INDEX
    Explanations

    ника

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fet
    -0.07
     aquí
    -0.07
    ή
    -0.06
    (Int
    -0.06
    tea
    -0.06
    essel
    -0.06
    azen
    -0.06
     dish
    -0.06
    Partner
    -0.06
    oten
    -0.06
    POSITIVE LOGITS
    ника
    0.17
    ник
    0.09
    нику
    0.08
    нике
    0.08
    [target
    0.07
     topLeft
    0.07
    ira
    0.07
     \""
    0.07
    ники
    0.07
     mAuth
    0.07
    Act Density 0.001%

    No Known Activations