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

    Neuronpedia

    INDEX
    Explanations

    advantages and disadvantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inherits
    -0.07
    kah
    -0.06
    ौ
    -0.06
    emap
    -0.06
     Kadın
    -0.06
    OAuth
    -0.06
    rhs
    -0.06
     خانه
    -0.06
     dedi
    -0.06
    oe
    -0.06
    POSITIVE LOGITS
    angstrom
    0.07
    езпеч
    0.07
    �
    0.06
     <:
    0.06
     Madame
    0.06
    increment
    0.06
    реп
    0.06
    (predicate
    0.06
    gesch
    0.06
    (DBG
    0.06
    Act Density 0.024%

    No Known Activations