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

    Neuronpedia

    INDEX
    Explanations

    platinum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hospital
    -0.07
    (member
    -0.07
    .complete
    -0.07
     사람들이
    -0.06
     detained
    -0.06
     jackets
    -0.06
    ために
    -0.06
     prostředí
    -0.06
    Friends
    -0.06
     enraged
    -0.06
    POSITIVE LOGITS
    الح
    0.07
    Imp
    0.07
    зв
    0.07
    cura
    0.07
    _symbol
    0.07
    밀
    0.06
    τι
    0.06
    銀
    0.06
    BMW
    0.06
    金
    0.06
    Act Density 0.027%

    No Known Activations