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

    Neuronpedia

    INDEX
    Explanations

    code with 'i'

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     projections
    -0.08
    χε
    -0.07
    ध
    -0.07
    ΜΑΤ
    -0.06
    America
    -0.06
    izzlies
    -0.06
     projected
    -0.06
     docking
    -0.06
     sided
    -0.06
     disclose
    -0.06
    POSITIVE LOGITS
    ليه
    0.06
     الذ
    0.06
    'field
    0.06
     trest
    0.06
     руках
    0.06
     Nova
    0.06
     Bee
    0.06
    'ye
    0.06
     klub
    0.06
     EXTRA
    0.06
    Act Density 0.079%

    No Known Activations