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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifact
    -0.07
    ентами
    -0.07
    93
    -0.06
    設計
    -0.06
     hill
    -0.06
     Justin
    -0.06
     Could
    -0.06
     week
    -0.06
    Stores
    -0.06
     talented
    -0.06
    POSITIVE LOGITS
     ecc
    0.07
    _FRAGMENT
    0.07
    oq
    0.07
     istediğiniz
    0.06
    τα
    0.06
    [ch
    0.06
    (sec
    0.06
     =>
↵
    0.06
     CIS
    0.06
     Μετα
    0.06
    Act Density 0.012%

    No Known Activations