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

    Neuronpedia

    INDEX
    Explanations

    journalistic transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Koreans
    -0.07
     nudity
    -0.07
     Hebrew
    -0.07
    itone
    -0.07
    Supply
    -0.07
    ливі
    -0.06
     kinky
    -0.06
    ixmap
    -0.06
    filtr
    -0.06
     Naruto
    -0.06
    POSITIVE LOGITS
    [Test
    0.06
     distributions
    0.06
     تلك
    0.06
    QPCP
    0.06
     stash
    0.06
     kurtul
    0.05
     discretion
    0.05
    LOAT
    0.05
    paredStatement
    0.05
    	index
    0.05
    Act Density 0.010%

    No Known Activations