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

    Neuronpedia

    INDEX
    Explanations

    shrinking rapidly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ontiti
    0.48
     ocurrió
    0.43
    createStatement
    0.43
     anys
    0.43
     recognises
    0.42
    ziła
    0.41
    irthday
    0.41
    RxDocument
    0.41
    achite
    0.40
    SPE
    0.40
    POSITIVE LOGITS
     hustle
    0.42
    我认为
    0.40
     Google
    0.40
     temptations
    0.40
     tors
    0.38
    掐
    0.36
    瞪
    0.36
     clutter
    0.36
    かれている
    0.36
     upset
    0.35
    Act Density 0.000%

    No Known Activations