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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mount
    -0.07
    irror
    -0.06
    acier
    -0.06
     texto
    -0.06
    gence
    -0.06
    ardu
    -0.06
    Vent
    -0.06
    ्टम
    -0.06
    арі
    -0.06
     ulus
    -0.06
    POSITIVE LOGITS
     Prep
    0.07
    (bits
    0.07
     prep
    0.07
     pena
    0.07
    ,data
    0.07
    (fb
    0.06
     leases
    0.06
     inspir
    0.06
    需要
    0.06
     Debbie
    0.06
    Act Density 0.008%

    No Known Activations