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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    م
    -0.07
     unavoid
    -0.07
     spreads
    -0.07
    mouse
    -0.07
     vertically
    -0.07
     Levi
    -0.06
     hitter
    -0.06
     amnesty
    -0.06
     sperm
    -0.06
     dot
    -0.06
    POSITIVE LOGITS
    (od
    0.06
    errorCode
    0.06
    аними
    0.06
     připom
    0.06
    дрес
    0.06
    ≦
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    	TokenName
    0.06
     نام
    0.06
    anki
    0.06
    Act Density 0.020%

    No Known Activations