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

    Neuronpedia

    INDEX
    Explanations

    Moth descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rotate
    -0.07
    Glass
    -0.07
     ﾞ
    -0.06
    ildren
    -0.06
    "strings
    -0.06
     DV
    -0.06
    _FETCH
    -0.06
     crime
    -0.06
    vh
    -0.06
     foil
    -0.06
    POSITIVE LOGITS
     Uns
    0.06
     编
    0.06
     manages
    0.06
    �
    0.06
    ><?=
    0.06
    _mentions
    0.06
    -com
    0.06
    นว
    0.06
     nutrient
    0.06
     تحلیل
    0.06
    Act Density 0.012%

    No Known Activations