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

    Neuronpedia

    INDEX
    Explanations

    programming components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANIEL
    0.57
    slüman
    0.55
    URNIZOR
    0.55
    MovementControls
    0.55
    ffekt
    0.52
    SANIT
    0.51
    <unused265>
    0.51
    positroid
    0.50
    YAN
    0.50
    యు
    0.49
    POSITIVE LOGITS
    '
    0.63
    ’
    0.57
    ::
    0.50
    ['
    0.48
    ၏
    0.48
    ["
    0.46
    님의
    0.45
     locale
    0.44
     refunds
    0.44
     "
    0.43
    Act Density 0.152%

    No Known Activations