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
     propose
    -0.06
    sig
    -0.06
    _Task
    -0.06
    -stop
    -0.06
     INTEGER
    -0.06
     BUY
    -0.06
    parse
    -0.06
    طال
    -0.06
    MU
    -0.06
    anooga
    -0.06
    POSITIVE LOGITS
    )]↵↵
    0.07
     screenings
    0.07
     Alberto
    0.07
     for
    0.06
    \xa
    0.06
     определ
    0.06
     факт
    0.06
    _attempts
    0.06
     Examiner
    0.06
     Alle
    0.06
    Act Density 0.024%

    No Known Activations