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

    Neuronpedia

    INDEX
    Explanations

    /copyleft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Classes
    -0.08
    Pred
    -0.07
     بأ
    -0.06
     Michel
    -0.06
    implify
    -0.06
    再
    -0.06
    üre
    -0.06
    	word
    -0.06
     fears
    -0.06
     halk
    -0.06
    POSITIVE LOGITS
    /copyleft
    0.08
    KeySpec
    0.07
    ?“↵↵
    0.07
     VID
    0.06
    ScreenState
    0.06
     Krishna
    0.06
     TObject
    0.06
     commercially
    0.06
     Ezek
    0.06
    .findByIdAndUpdate
    0.06
    Act Density 0.001%

    No Known Activations