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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Signs
    -0.07
     floats
    -0.07
     slightly
    -0.07
     individually
    -0.06
    .Hand
    -0.06
     signs
    -0.06
     seekers
    -0.06
     desired
    -0.06
    чат
    -0.06
     Lunar
    -0.06
    POSITIVE LOGITS
     Many
    0.07
    "G
    0.07
     oppressive
    0.07
    .And
    0.07
     many
    0.07
    Many
    0.07
    　
    0.06
    по
    0.06
    OpenHelper
    0.06
     πολ
    0.06
    Act Density 0.018%

    No Known Activations