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

    Neuronpedia

    INDEX
    Explanations

    specific number or name followed by descriptive noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     җиңү
    1.00
     увеличить
    0.96
    儩
    0.89
    ayutt
    0.89
    퐫
    0.89
     уйнау
    0.88
    क्टर
    0.88
    ayvachi
    0.88
     уйнарга
    0.88
     Cáceres
    0.88
    POSITIVE LOGITS
    d
    0.92
     car
    0.77
    mag
    0.76
    id
    0.73
    .
    0.72
    car
    0.70
    -
    0.70
    '
    0.69
    rig
    0.68
    rent
    0.68
    Act Density 0.000%

    No Known Activations