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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irrit
    -0.07
    ३
    -0.06
    Ionic
    -0.06
    ۱۱
    -0.06
    ๑
    -0.06
    ději
    -0.06
    mgr
    -0.06
     antigen
    -0.06
    League
    -0.06
    함
    -0.06
    POSITIVE LOGITS
     durum
    0.07
     浙江
    0.07
     forums
    0.06
     Berger
    0.06
     comprised
    0.06
    rike
    0.06
     (*)
    0.06
    кав
    0.06
     레이
    0.06
    _principal
    0.06
    Act Density 0.023%

    No Known Activations