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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुम
    -0.07
    ):\
    -0.06
    clid
    -0.06
     albums
    -0.06
     Messaging
    -0.06
     ATH
    -0.06
    _fill
    -0.06
     _)
    -0.06
     palindrome
    -0.06
    gent
    -0.06
    POSITIVE LOGITS
     instit
    0.07
    (Student
    0.07
     organisers
    0.07
    ưới
    0.07
     мають
    0.07
    iseconds
    0.06
    乂
    0.06
    #![
    0.06
     humiliation
    0.06
     Successfully
    0.06
    Act Density 0.130%

    No Known Activations