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

    Neuronpedia

    INDEX
    Explanations

    80

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     підготов
    -0.07
     Mavericks
    -0.07
     ignores
    -0.07
     tej
    -0.06
    каж
    -0.06
     assertion
    -0.06
    езпеч
    -0.06
     ajud
    -0.06
     unread
    -0.06
    Depart
    -0.06
    POSITIVE LOGITS
    _OPER
    0.07
    ंदर
    0.06
    bear
    0.06
     separator
    0.06
    CompanyName
    0.06
     التح
    0.06
     boiling
    0.06
    PP
    0.06
    Blend
    0.06
    hong
    0.06
    Act Density 0.002%

    No Known Activations