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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    几种
    -0.07
    떻
    -0.07
     Radiation
    -0.07
     protect
    -0.07
    loor
    -0.07
     호텔
    -0.06
    תקציב
    -0.06
    ﺉ
    -0.06
    ﭦ
    -0.06
    (Module
    -0.06
    POSITIVE LOGITS
     côt
    0.07
     lows
    0.07
     flavour
    0.07
     recalling
    0.07
    �
    0.07
    /O
    0.07
    荑
    0.07
     derog
    0.07
     gating
    0.07
    -plus
    0.07
    Act Density 0.005%

    No Known Activations