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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     événements
    -0.08
     लाइ
    -0.08
     उल
    -0.08
     réseaux
    -0.07
    ейтинг
    -0.07
     blacklist
    -0.07
     warnings
    -0.07
     unilateral
    -0.07
     Bibli
    -0.07
     Clear
    -0.07
    POSITIVE LOGITS
     earthy
    0.08
    .optimizer
    0.08
     midfield
    0.08
    aders
    0.08
     optimum
    0.07
     Bho
    0.07
     selectively
    0.07
     Macbeth
    0.07
    Moved
    0.07
     exert
    0.07
    Act Density 0.032%

    No Known Activations