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

    Neuronpedia

    INDEX
    Explanations

    organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لمان
    -0.06
     gui
    -0.06
     Turk
    -0.06
     налог
    -0.06
     monday
    -0.06
    excluding
    -0.06
    _DGRAM
    -0.06
    �
    -0.06
    igte
    -0.05
    ализи
    -0.05
    POSITIVE LOGITS
     cravings
    0.07
    ض
    0.06
    (Object
    0.06
     culmination
    0.06
    Another
    0.06
     Object
    0.06
    ottesville
    0.06
     �
    0.06
    'It
    0.06
    ाधन
    0.06
    Act Density 0.104%

    No Known Activations