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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accreditation
    -0.08
     accredited
    -0.08
     empowers
    -0.08
    と言
    -0.07
    Parity
    -0.07
     meetings
    -0.07
     neuroscience
    -0.07
    tested
    -0.07
     같습니다
    -0.07
     પહોંચી
    -0.07
    POSITIVE LOGITS
     darker
    0.12
     believable
    0.11
     realism
    0.10
     foliage
    0.10
     decorative
    0.10
     realistic
    0.10
     размест
    0.10
     italic
    0.10
     faint
    0.10
     декоратив
    0.09
    Act Density 0.020%

    No Known Activations