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

    Neuronpedia

    INDEX
    Explanations

    Arithmetic/Mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filmmakers
    -0.08
     পুলিশের
    -0.08
     حلق
    -0.08
    ակի
    -0.08
    сыл
    -0.08
    ೃತ್ತ
    -0.08
    USP
    -0.08
     گرفتار
    -0.08
    repid
    -0.08
    ustada
    -0.07
    POSITIVE LOGITS
     Addition
    0.11
    .vstack
    0.10
     addition
    0.10
     össze
    0.09
    Subtract
    0.09
    Addition
    0.09
     Bedding
    0.09
    _bottom
    0.09
     stacked
    0.09
     Lines
    0.09
    Act Density 0.028%

    No Known Activations