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

    Neuronpedia

    INDEX
    Explanations

    firing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ste
    -0.07
     Neon
    -0.07
    stitute
    -0.07
    稚
    -0.07
    ูก
    -0.07
    esian
    -0.07
     "@/
    -0.07
    تاب
    -0.06
    scopic
    -0.06
    roupon
    -0.06
    POSITIVE LOGITS
    -mails
    0.07
    maal
    0.07
     Росс
    0.07
    _RESULT
    0.07
    .presentation
    0.07
     rá
    0.07
    رحم
    0.06
    〶
    0.06
    大气
    0.06
     무
    0.06
    Act Density 0.008%

    No Known Activations