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

    Neuronpedia

    INDEX
    Explanations

    data, material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpretations
    -0.08
     senses
    -0.07
    🌂
    -0.07
    olley
    -0.07
     Fucked
    -0.07
     aucun
    -0.07
    拮
    -0.07
    موس
    -0.07
    cel
    -0.07
     peoples
    -0.07
    POSITIVE LOGITS
     inbox
    0.07
     stated
    0.07
    .AppendLine
    0.07
    硬盘
    0.07
    さ
    0.07
     squads
    0.07
    ))]↵
    0.06
     [
    0.06
     army
    0.06
    (bool
    0.06
    Act Density 0.002%

    No Known Activations