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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相信
    -0.07
     -------------------------------------------------------------------------↵
    -0.06
     precious
    -0.06
    ؟؟
    -0.06
    −
    -0.06
    horn
    -0.06
     merak
    -0.06
     Kardashian
    -0.06
     metres
    -0.06
    isEqual
    -0.06
    POSITIVE LOGITS
    еб
    0.07
    (Card
    0.06
     outsiders
    0.06
    _sys
    0.06
    Opt
    0.06
    -Sh
    0.06
     parent
    0.06
    	pr
    0.06
    Neo
    0.06
    Motion
    0.06
    Act Density 0.000%

    No Known Activations