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

    Neuronpedia

    INDEX
    Explanations

    connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    損
    -0.06
     lhs
    -0.06
     inaccur
    -0.06
     푸
    -0.06
    868
    -0.06
    (dl
    -0.06
     бра
    -0.06
    ーダ
    -0.06
    dest
    -0.06
     custom
    -0.06
    POSITIVE LOGITS
    _parms
    0.07
     pública
    0.07
    EMALE
    0.07
    ,'']]],↵
    0.07
     фіз
    0.07
     artillery
    0.06
    _parameters
    0.06
    NSDictionary
    0.06
    ість
    0.06
    emodel
    0.06
    Act Density 0.237%

    No Known Activations