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

    Neuronpedia

    INDEX
    Explanations

    code related tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bservable
    -0.07
    ibe
    -0.06
     east
    -0.06
     muh
    -0.06
    pixels
    -0.06
     uncovered
    -0.06
    ｯ
    -0.06
    (random
    -0.06
    ishly
    -0.06
    Stats
    -0.06
    POSITIVE LOGITS
     Zot
    0.07
     Bron
    0.07
     ETF
    0.06
     intimacy
    0.06
     Industrial
    0.06
     США
    0.06
     серьез
    0.06
    єш
    0.06
    -expression
    0.06
    ndon
    0.06
    Act Density 0.185%

    No Known Activations