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

    Neuronpedia

    INDEX
    Explanations

    End of lines of code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inserts
    -0.07
    umes
    -0.07
    Because
    -0.06
     shuffled
    -0.06
     hypothetical
    -0.06
    attack
    -0.06
    hydr
    -0.06
    =nil
    -0.06
     both
    -0.06
    Reality
    -0.06
    POSITIVE LOGITS
    ทำ
    0.08
     yapmaya
    0.06
     gemeins
    0.06
     [+
    0.06
    的事情
    0.06
     autogenerated
    0.06
    лика
    0.06
     سنة
    0.06
    favorite
    0.06
    .dateFormat
    0.06
    Act Density 0.008%

    No Known Activations