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

    Neuronpedia

    INDEX
    Explanations

    banks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    versation
    -0.07
    олош
    -0.07
     birinin
    -0.07
     подіб
    -0.06
    κυ
    -0.06
    =(↵
    -0.06
    aların
    -0.06
    стве
    -0.06
     aujourd
    -0.06
     днів
    -0.06
    POSITIVE LOGITS
    _DISABLE
    0.07
     expanding
    0.07
     preserves
    0.07
    �
    0.07
     horizontally
    0.07
     вывод
    0.06
     Kale
    0.06
    .psi
    0.06
     выс
    0.06
     Talking
    0.06
    Act Density 0.014%

    No Known Activations