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

    Neuronpedia

    INDEX
    Explanations

    implemented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↑
    -0.07
    mesine
    -0.07
     सदस
    -0.07
    ressed
    -0.07
     ACE
    -0.07
    .items
    -0.06
    database
    -0.06
    ,:,:
    -0.06
     patience
    -0.06
    _user
    -0.06
    POSITIVE LOGITS
     implemented
    0.09
    (option
    0.06
    currentColor
    0.06
    .scalablytyped
    0.06
    .openConnection
    0.06
    latest
    0.06
    getDisplay
    0.06
    iphone
    0.06
    كل
    0.06
     hé
    0.06
    Act Density 0.017%

    No Known Activations