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

    Neuronpedia

    INDEX
    Explanations

    numbers related to 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lukan
    1.02
    nesday
    1.02
     अनु
    0.98
    ares
    0.97
    น์
    0.97
    র্ষি
    0.95
    enting
    0.95
     একা
    0.94
    ㄨ
    0.92
    ări
    0.92
    POSITIVE LOGITS
    1.32
    corners
    1.31
     quadrants
    1.25
    ঠা
    1.23
    kates
    1.16
    Corners
    1.15
     pagal
    1.15
    ⣶
    1.14
     leptons
    1.14
    ি
    1.12
    Act Density 0.238%

    No Known Activations