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

    Neuronpedia

    INDEX
    Explanations

    unordered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     damping
    -0.09
    λά
    -0.08
     אַנ
    -0.08
    アン
    -0.08
    نال
    -0.08
     दुनिया
    -0.07
     δρά
    -0.07
     ansin
    -0.07
     Всем
    -0.07
     تدخل
    -0.07
    POSITIVE LOGITS
     newest
    0.08
    (condition
    0.08
    üns
    0.08
    _due
    0.07
     CONDITION
    0.07
    (keyword
    0.07
    _CONN
    0.07
    ільки
    0.07
     uniq
    0.07
    _conditions
    0.07
    Act Density 0.001%

    No Known Activations