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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inski
    -0.07
     decks
    -0.07
    /********
    -0.07
     SL
    -0.06
     booths
    -0.06
     seeing
    -0.06
     Rouge
    -0.06
    ág
    -0.06
    even
    -0.06
     trains
    -0.06
    POSITIVE LOGITS
    .I
    0.07
    (Application
    0.07
    setCurrent
    0.07
    .Expression
    0.07
     projectile
    0.07
     밀
    0.06
    	Namespace
    0.06
    ві
    0.06
    mpl
    0.06
     Utf
    0.06
    Act Density 0.001%

    No Known Activations