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

    Neuronpedia

    INDEX
    Explanations

    model modelmodel identity and origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    滪
    0.45
    帳に追加
    0.43
    टान
    0.43
     কর্নে
    0.42
     tumeurs
    0.42
    砳
    0.41
    ឡិចត្រូ
    0.41
     reformas
    0.41
     फडण
    0.41
    ▟
    0.41
    POSITIVE LOGITS
    7
    0.45
     and
    0.41
    0.38
    5
    0.38
    …
    0.36
     Designer
    0.36
    si
    0.35
     ay
    0.35
    0
    0.35
    band
    0.35
    Act Density 0.037%

    No Known Activations