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

    Neuronpedia

    INDEX
    Explanations

    new appointments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ガ
    -0.07
    imet
    -0.07
     spécialisé
    -0.07
     Поэтому
    -0.07
    室
    -0.07
    -room
    -0.07
    咖
    -0.07
     submitting
    -0.07
    窗口
    -0.07
    ﺥ
    -0.07
    POSITIVE LOGITS
     Cant
    0.08
    لوح
    0.07
     Gathering
    0.07
     Needs
    0.07
     הש
    0.07
     Katrina
    0.07
     בח
    0.06
     באי
    0.06
    銮
    0.06
     Audrey
    0.06
    Act Density 0.060%

    No Known Activations