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

    Neuronpedia

    INDEX
    Explanations

    quantities, measurements, and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ADDE
    -0.09
     âĮĴ
    -0.08
    EMPLARY
    -0.08
    vrier
    -0.08
    shint
    -0.08
    -urlencoded
    -0.08
    sembles
    -0.08
    icari
    -0.08
     ficken
    -0.08
     hete
    -0.08
    POSITIVE LOGITS
     Briggs
    0.08
    com
    0.08
     Spear
    0.08
    _____
    0.08
    aron
    0.08
    vido
    0.08
    typings
    0.07
     SavaÅŁ
    0.07
    IM
    0.07
    ardo
    0.07
    Act Density 0.178%

    No Known Activations