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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Media
    -0.08
     attracted
    -0.06
     Hundreds
    -0.06
     关
    -0.06
     undergoing
    -0.06
     notices
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
    -floating
    -0.06
    <html
    -0.06
     Dump
    -0.06
    POSITIVE LOGITS
    δι
    0.08
     dé
    0.07
     tướng
    0.07
    _rotate
    0.07
     싱
    0.07
    StoryboardSegue
    0.06
    ENDED
    0.06
     někdo
    0.06
     devuelve
    0.06
    ฒ
    0.06
    Act Density 0.000%

    No Known Activations