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

    Neuronpedia

    INDEX
    Explanations

    Full Name country country short name ISO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ("
    1.02
     [§
    0.96
    Supplemental
    0.87
    potentially
    0.86
    Ō
    0.85
    Pokémon
    0.84
    !)
    0.82
    California
    0.82
     naï
    0.81
    ␤
    0.81
    POSITIVE LOGITS
     equipments
    1.98
     squre
    1.74
     গুলো
    1.67
     গুলোতে
    1.61
     upto
    1.59
     loosing
    1.58
     kerala
    1.54
    wellery
    1.53
     های
    1.52
     atleast
    1.50
    Act Density 0.235%

    No Known Activations