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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _height
    -0.07
    sts
    -0.07
    992
    -0.07
     clue
    -0.07
    appear
    -0.07
     (?,
    -0.06
    ,-
    -0.06
    -(
    -0.06
     radiator
    -0.06
    404
    -0.06
    POSITIVE LOGITS
    �
    0.08
     kendisini
    0.07
     peč
    0.07
    ديث
    0.06
    ’est
    0.06
     Cir
    0.06
     fikir
    0.06
     Vị
    0.06
    Tak
    0.06
     özelliği
    0.06
    Act Density 0.071%

    No Known Activations