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

    Neuronpedia

    INDEX
    Explanations

    traversing space or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”،
    0.98
    ко
    0.95
    ি
    0.95
    apayati
    0.93
    c
    0.91
    ാ
    0.90
     gacche
    0.89
     đều
    0.89
    ิ
    0.89
     vadati
    0.88
    POSITIVE LOGITS
    '
    1.24
     through
    1.13
     with
    1.05
    ל
    1.04
    ت
    1.00
    你
    0.98
    通过
    0.98
    ého
    0.97
    at
    0.96
    (
    0.95
    Act Density 0.047%

    No Known Activations