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

    Neuronpedia

    INDEX
    Explanations

    cultures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     necessities
    -0.06
    LOAT
    -0.06
    deny
    -0.06
     خیابان
    -0.06
     gunfire
    -0.06
    _context
    -0.06
    _zeros
    -0.06
     ομά
    -0.06
     kab
    -0.06
    集团
    -0.06
    POSITIVE LOGITS
    Generally
    0.07
    ATORS
    0.06
     redund
    0.06
    Managing
    0.06
     Hoover
    0.06
    means
    0.06
    (reordered
    0.06
    310
    0.06
    rika
    0.06
    sPid
    0.06
    Act Density 0.020%

    No Known Activations