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

    Neuronpedia

    INDEX
    Explanations

    game scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pager
    -0.07
    aycast
    -0.06
     Teaching
    -0.06
     CoreData
    -0.06
     Flag
    -0.06
     policing
    -0.06
    _US
    -0.06
    )->
    -0.06
    Logic
    -0.06
    ivar
    -0.06
    POSITIVE LOGITS
    datos
    0.07
     têm
    0.07
     віль
    0.07
     deported
    0.06
    pers
    0.06
    071
    0.06
     مع
    0.06
     ऋ
    0.06
     आप
    0.06
     факти
    0.06
    Act Density 0.169%

    No Known Activations