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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heroine
    -0.07
     Stroke
    -0.06
    Badge
    -0.06
    ứng
    -0.06
     CX
    -0.06
    .Reverse
    -0.06
     />
↵
    -0.06
     nurture
    -0.06
    _capabilities
    -0.06
    _REDIRECT
    -0.06
    POSITIVE LOGITS
     inspirational
    0.07
     опера
    0.06
    ifdef
    0.06
     číslo
    0.06
    .algorithm
    0.06
     김
    0.06
     stopping
    0.06
    taken
    0.06
     Jung
    0.06
    則
    0.06
    Act Density 0.025%

    No Known Activations