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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    't
    -0.07
     Walters
    -0.07
     Services
    -0.07
     Dell
    -0.06
    ’t
    -0.06
     زوج
    -0.06
    :relative
    -0.06
     Iron
    -0.06
     roy
    -0.06
    Girls
    -0.06
    POSITIVE LOGITS
    허
    0.07
    	assertNotNull
    0.07
    hour
    0.07
    _rgba
    0.07
    ngör
    0.07
    	pc
    0.07
    coeff
    0.06
    =(↵
    0.06
     персп
    0.06
    Votes
    0.06
    Act Density 0.133%

    No Known Activations