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

    Neuronpedia

    INDEX
    Explanations

    code-related special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Compute
    -0.07
    日凌晨
    -0.07
    [left
    -0.07
    [from
    -0.07
    (IConfiguration
    -0.07
     Wich
    -0.07
     Src
    -0.07
     Miscellaneous
    -0.06
     max
    -0.06
     _.
    -0.06
    POSITIVE LOGITS
    velt
    0.07
     Buttons
    0.07
    oor
    0.07
    ﯡ
    0.06
    季后赛
    0.06
     jugar
    0.06
    ateurs
    0.06
    OfString
    0.06
     thermostat
    0.06
    演出
    0.06
    Act Density 0.024%

    No Known Activations