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

    Neuronpedia

    INDEX
    Explanations

    Mentions the word "word"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .kill
    -0.06
     montage
    -0.06
     devote
    -0.06
    孙
    -0.06
     Socorro
    -0.06
    jong
    -0.06
    like
    -0.06
     tam
    -0.06
     extern
    -0.06
     edition
    -0.06
    POSITIVE LOGITS
    抽
    0.08
    Updates
    0.07
    _AXIS
    0.06
    (mi
    0.06
     SCI
    0.06
    masında
    0.06
     FAG
    0.06
     continuously
    0.06
     znovu
    0.06
    _master
    0.06
    Act Density 0.043%

    No Known Activations