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

    Neuronpedia

    INDEX
    Explanations

    code/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Speak
    -0.10
     Speaking
    -0.09
    Speak
    -0.09
     speak
    -0.08
     మాట్లాడ
    -0.08
     konuş
    -0.08
     לד
    -0.08
     speaker
    -0.08
    制定
    -0.08
     സംസാര
    -0.08
    POSITIVE LOGITS
    "github
    0.09
     gor
    0.08
     जाते
    0.08
    providers
    0.08
    PEc
    0.08
    .mods
    0.08
    .clean
    0.08
     inspires
    0.08
     contrib
    0.08
     provenientes
    0.08
    Act Density 0.002%

    No Known Activations