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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fw
    -0.07
     Arg
    -0.07
    JsonValue
    -0.06
    -dess
    -0.06
    igm
    -0.06
     ссыл
    -0.06
     conditioning
    -0.06
     poč
    -0.06
    ucch
    -0.06
     était
    -0.06
    POSITIVE LOGITS
     Sure
    0.07
    Produ
    0.06
    ีฬ
    0.06
    mounted
    0.06
    vasion
    0.06
    RATE
    0.06
     Describe
    0.06
    шт
    0.06
    (man
    0.06
    bes
    0.06
    Act Density 0.010%

    No Known Activations