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

    Neuronpedia

    INDEX
    Explanations

    reach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     должно
    -0.06
    경
    -0.06
    tems
    -0.06
    writes
    -0.06
    {}]
    -0.06
     itibar
    -0.06
     mildly
    -0.06
    .tel
    -0.06
    /ap
    -0.06
    POSITIVE LOGITS
     PLC
    0.07
    =form
    0.06
    .ui
    0.06
     guilty
    0.06
    чин
    0.06
     contribute
    0.06
     earm
    0.06
    бе
    0.06
    .numberOfLines
    0.06
     iler
    0.06
    Act Density 0.025%

    No Known Activations