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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bright
    -0.09
     Walsh
    -0.09
    bright
    -0.08
     Advertisement
    -0.08
    Visibility
    -0.08
     animé
    -0.08
    _tail
    -0.07
     booth
    -0.07
    楽し
    -0.07
     tail
    -0.07
    POSITIVE LOGITS
     detox
    0.10
    中的
    0.09
    -wide
    0.08
     tissues
    0.08
     interconnected
    0.08
     metabolism
    0.08
     Lle
    0.08
     defenses
    0.08
    에게
    0.08
     autoimmune
    0.08
    Act Density 0.018%

    No Known Activations