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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Adult
    -0.06
    .wh
    -0.06
    IOC
    -0.06
    (th
    -0.06
     musician
    -0.06
     measurable
    -0.06
     ISC
    -0.06
    fen
    -0.06
     Brent
    -0.06
    Seat
    -0.05
    POSITIVE LOGITS
     smack
    0.08
     ober
    0.07
    unde
    0.06
    رج
    0.06
     acupuncture
    0.06
     Sang
    0.06
     mur
    0.06
     feminists
    0.06
    ACEMENT
    0.06
     halluc
    0.06
    Act Density 0.003%

    No Known Activations