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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пор
    -0.07
     písem
    -0.06
    erer
    -0.06
    .tc
    -0.06
     APC
    -0.06
    ifice
    -0.06
     Ba
    -0.06
    umbing
    -0.06
    걸
    -0.06
     grind
    -0.06
    POSITIVE LOGITS
     teaspoons
    0.07
    _fold
    0.06
    [loc
    0.06
     […
    0.06
     nossa
    0.06
    阶段
    0.06
     ontvangst
    0.06
     retrieves
    0.06
    /chat
    0.06
     Akt
    0.06
    Act Density 0.037%

    No Known Activations