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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çek
    -0.07
    atrix
    -0.07
     Hussein
    -0.07
     pasar
    -0.07
     marché
    -0.07
    �
    -0.07
     CROSS
    -0.07
     chân
    -0.06
    geh
    -0.06
    쓰
    -0.06
    POSITIVE LOGITS
     reminders
    0.07
    hint
    0.07
    untu
    0.07
    _BAND
    0.07
    值得一提
    0.07
    Important
    0.07
    ttp
    0.07
    ᐝ
    0.07
    👙
    0.07
    apot
    0.07
    Act Density 0.001%

    No Known Activations