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

    Neuronpedia

    INDEX
    Explanations

    sizes and textures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rice
    -0.07
     bic
    -0.07
     trustees
    -0.06
     tapes
    -0.06
     demonstr
    -0.06
     Ms
    -0.06
     jean
    -0.06
    Indexed
    -0.06
    orch
    -0.06
     انتشار
    -0.06
    POSITIVE LOGITS
    end
    0.07
     verdade
    0.07
    iveness
    0.07
     Belgium
    0.06
    appiness
    0.06
     mại
    0.06
    "));↵↵
    0.06
    无码
    0.06
     '';↵↵
    0.06
    олод
    0.06
    Act Density 0.063%

    No Known Activations