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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    larım
    -0.07
     француз
    -0.07
     luckily
    -0.06
     물
    -0.06
    izyon
    -0.06
    adele
    -0.06
     начала
    -0.06
     disput
    -0.06
     Müslüman
    -0.06
    ость
    -0.06
    POSITIVE LOGITS
     stal
    0.07
    _CONT
    0.07
     remodel
    0.06
    Il
    0.06
    setCurrent
    0.06
    �
    0.06
     В
    0.06
    _books
    0.06
    Canonical
    0.06
    �
    0.06
    Act Density 0.049%

    No Known Activations