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

    Neuronpedia

    INDEX
    Explanations

    Random snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -k
    -0.07
     dah
    -0.06
    haf
    -0.06
    aes
    -0.06
    ();↵↵
    -0.06
    ntag
    -0.06
    ξι
    -0.06
     qed
    -0.06
     я
    -0.06
     anguish
    -0.06
    POSITIVE LOGITS
    []={
    0.06
    afone
    0.06
    ラン
    0.06
    /person
    0.06
    }/${
    0.06
     party
    0.06
    距離
    0.06
    Exercise
    0.06
     errorMessage
    0.06
    ازي
    0.06
    Act Density 0.000%

    No Known Activations