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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ariance
    -0.07
    Thing
    -0.07
     grinding
    -0.07
    JP
    -0.07
    .Preference
    -0.07
    اقة
    -0.06
    ('?
    -0.06
     Kosten
    -0.06
    ้เก
    -0.06
    уст
    -0.06
    POSITIVE LOGITS
    taş
    0.07
    kyt
    0.07
     Syracuse
    0.06
    @Xml
    0.06
     scr
    0.06
    darwin
    0.06
    ))];↵
    0.06
    Titles
    0.06
     sides
    0.06
     shitty
    0.06
    Act Density 0.011%

    No Known Activations