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

    Neuronpedia

    INDEX
    Explanations

    verbs that have to do with production, performance, or manipulation

    oai_token-act-pair · gemini-2.0-flash

    Legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.65
     jouets
    -0.57
     répondu
    -0.57
     piattaforma
    -0.53
     inoxydable
    -0.50
    articolo
    -0.50
     déploy
    -0.50
    ándolos
    -0.50
     scaricare
    -0.49
     vechi
    -0.49
    POSITIVE LOGITS
    IGraphics
    0.59
     ویکی‌پدی
    0.56
    NameInMap
    0.56
    ineas
    0.55
     surveys
    0.54
     lifes
    0.53
     whee
    0.53
     demos
    0.52
    timed
    0.52
     videos
    0.52
    Act Density 1.620%

    No Known Activations