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

    Neuronpedia

    INDEX
    Explanations

    highly motivated and dedicated professionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avacanam
    0.43
    ことなく
    0.43
     ہو۔
    0.42
    インター
    0.42
    法律
    0.42
    increased
    0.41
    ’?
    0.41
    ဏ်
    0.40
    ൩
    0.40
    筆
    0.40
    POSITIVE LOGITS
    brom
    0.45
     getest
    0.42
     Bu
    0.41
     Rot
    0.41
    و
    0.40
     volum
    0.40
     brom
    0.39
     Teile
    0.39
     Peut
    0.39
     और
    0.39
    Act Density 0.005%

    No Known Activations