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

    Neuronpedia

    INDEX
    Explanations

    multiplicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     시장
    -0.06
     XCTest
    -0.06
     pomáh
    -0.06
     cleansing
    -0.06
    -tank
    -0.06
    hay
    -0.06
    قام
    -0.06
     trust
    -0.06
    侯
    -0.06
    jad
    -0.06
    POSITIVE LOGITS
     especial
    0.06
    алю
    0.06
     attent
    0.06
    _Begin
    0.06
    /random
    0.06
    best
    0.06
    はない
    0.06
     Blow
    0.06
     Petty
    0.06
    :max
    0.06
    Act Density 0.144%

    No Known Activations