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

    Neuronpedia

    INDEX
    Explanations

    items and concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logarithms
    0.64
    drain
    0.63
    sailboat
    0.63
     rootView
    0.62
     znamená
    0.62
    prüfung
    0.61
     isother
    0.60
    approximation
    0.60
    englisch
    0.59
     logarith
    0.59
    POSITIVE LOGITS
     "
    0.66
     -"
    0.65
    )"
    0.63
     '
    0.61
     DE
    0.60
     Alone
    0.58
    ]"
    0.58
    ae
    0.57
    ："
    0.57
    "
    0.57
    Act Density 0.000%

    No Known Activations