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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Languages
    -0.07
     White
    -0.07
    /group
    -0.07
     γνω
    -0.06
     impartial
    -0.06
     Supplier
    -0.06
     Depart
    -0.06
     pinned
    -0.06
     alignments
    -0.06
     ум
    -0.06
    POSITIVE LOGITS
     reflective
    0.06
     cư
    0.06
    lation
    0.06
    RESET
    0.06
     InputDecoration
    0.06
    査
    0.06
    ارب
    0.06
    ADDR
    0.06
    0.06
     RelayCommand
    0.06
    Act Density 0.005%

    No Known Activations