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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    困
    -0.07
     جذ
    -0.06
     �
    -0.06
    μένο
    -0.06
    �
    -0.06
     robbed
    -0.06
    (Equal
    -0.06
    followers
    -0.06
    ██
    -0.06
     düşman
    -0.06
    POSITIVE LOGITS
     Downs
    0.07
    @Json
    0.06
     Presenter
    0.06
     Lös
    0.06
    onation
    0.06
    /im
    0.06
    .fromRGBO
    0.06
     DeV
    0.06
    .readInt
    0.06
    　i
    0.06
    Act Density 0.012%

    No Known Activations