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

    Neuronpedia

    INDEX
    Explanations

    induction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sitemap
    -0.06
     suchen
    -0.06
     WK
    -0.06
     сотруд
    -0.06
    iqu
    -0.06
    beeld
    -0.06
    arefa
    -0.06
    alim
    -0.06
     silent
    -0.06
    (The
    -0.06
    POSITIVE LOGITS
     lá
    0.06
     мг
    0.06
    0.06
    入り
    0.06
    }:{
    0.06
    India
    0.06
     leisure
    0.06
    _patterns
    0.06
     induces
    0.06
     MLA
    0.06
    Act Density 0.002%

    No Known Activations