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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addElement
    -0.06
    にする
    -0.06
     Harrison
    -0.06
    .show
    -0.06
    ｯ
    -0.06
     Refriger
    -0.06
     Nate
    -0.06
     ridicule
    -0.06
     akan
    -0.05
     AssemblyProduct
    -0.05
    POSITIVE LOGITS
     six
    0.07
    ποιη
    0.07
     squeez
    0.07
    cop
    0.07
    _dec
    0.07
     guards
    0.07
    Selection
    0.07
     inhab
    0.06
    istically
    0.06
    246
    0.06
    Act Density 0.005%

    No Known Activations