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

    Neuronpedia

    INDEX
    Explanations

    paradigms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tubuh
    -0.08
     bodybuilding
    -0.08
    usuf
    -0.07
     bier
    -0.07
    芸
    -0.07
     Kick
    -0.07
     conçu
    -0.07
     "=
    -0.07
    benef
    -0.07
    达人
    -0.07
    POSITIVE LOGITS
     worldview
    0.14
     paradigma
    0.13
     paradigm
    0.13
     paradig
    0.13
     radically
    0.12
     बदलाव
    0.12
     Parad
    0.11
     overhaul
    0.11
     تغيير
    0.11
     ænd
    0.11
    Act Density 0.027%

    No Known Activations