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

    Neuronpedia

    INDEX
    Explanations

    Columbia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offset
    -0.08
     oat
    -0.07
    acos
    -0.07
    Ҥ
    -0.07
     Interviews
    -0.07
     Mind
    -0.07
    ريط
    -0.07
    Todd
    -0.07
     chứ
    -0.06
    acad
    -0.06
    POSITIVE LOGITS
    Ｇ
    0.07
     Floors
    0.07
    ᄂ
    0.07
    olumbia
    0.07
    클
    0.07
     gypsum
    0.07
    >");
↵
    0.07
    ⬊
    0.07
    ⁂
    0.06
     longing
    0.06
    Act Density 0.011%

    No Known Activations