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

    Neuronpedia

    INDEX
    Explanations

    Code/Copyright Notices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	step
    -0.08
     pov
    -0.08
    strength
    -0.07
    _BITMAP
    -0.07
    ACK
    -0.07
     Worm
    -0.07
    _CONV
    -0.07
    _TASK
    -0.07
    告訴
    -0.07
     Tactical
    -0.07
    POSITIVE LOGITS
    uct
    0.07
     аренд
    0.07
    网吧
    0.07
    ╄
    0.07
     الثال
    0.07
    熛
    0.07
    образ
    0.07
     moż
    0.07
    ħ
    0.07
    初三
    0.07
    Act Density 0.007%

    No Known Activations