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

    Neuronpedia

    INDEX
    Explanations

    statistical inference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ar
    -0.07
     асп
    -0.06
    (mysql
    -0.06
     люди
    -0.06
     Binary
    -0.06
     arity
    -0.06
     originates
    -0.06
     Пари
    -0.06
     bureaucratic
    -0.06
     رای
    -0.06
    POSITIVE LOGITS
    iagnostics
    0.07
    深圳
    0.06
     inference
    0.06
     Releases
    0.06
     ersten
    0.06
     nesting
    0.06
     المل
    0.06
     oli
    0.06
     letzten
    0.06
    じ
    0.06
    Act Density 0.004%

    No Known Activations