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

    Neuronpedia

    INDEX
    Explanations

    instead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Streaming
    -0.07
     Bracket
    -0.07
    abilities
    -0.06
    (category
    -0.06
     Ry
    -0.06
     rated
    -0.06
    ़ों
    -0.06
    송
    -0.06
     Religious
    -0.06
     buffered
    -0.06
    POSITIVE LOGITS
     instead
    0.07
    Yahoo
    0.07
    nth
    0.07
    .goBack
    0.07
     nineteenth
    0.07
    (inp
    0.06
     centro
    0.06
     downside
    0.06
    گونه
    0.06
     dönemde
    0.06
    Act Density 0.006%

    No Known Activations