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

    Neuronpedia

    INDEX
    Explanations

    Legal case context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Զ
    -0.07
    アジ
    -0.07
    榇
    -0.07
    detach
    -0.07
    觑
    -0.07
    Dismiss
    -0.07
    醑
    -0.07
     сентя
    -0.07
     JsonSerializer
    -0.07
     ту
    -0.07
    POSITIVE LOGITS
     Todo
    0.07
     Gone
    0.07
     advocating
    0.07
    _CM
    0.07
     Social
    0.07
     Comm
    0.07
    umping
    0.07
     workbook
    0.06
    协调
    0.06
    walls
    0.06
    Act Density 0.016%

    No Known Activations