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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     headaches
    -0.07
     buzz
    -0.07
    的手
    -0.07
     Ingen
    -0.06
    tical
    -0.06
    _not
    -0.06
     Haz
    -0.06
     hastily
    -0.06
     Knot
    -0.06
    .setItem
    -0.06
    POSITIVE LOGITS
    μ
    0.08
    .ipv
    0.07
    .',
    0.07
    498
    0.07
     socks
    0.07
    �
    0.07
     รวม
    0.07
    ент
    0.07
    ADMIN
    0.06
    ore
    0.06
    Act Density 0.004%

    No Known Activations