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

    Neuronpedia

    INDEX
    Explanations

    say ending -on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.07
     phiếu
    -0.06
    ць
    -0.06
     endangered
    -0.06
     menc
    -0.06
    Sum
    -0.06
    .sig
    -0.06
    _preview
    -0.06
    id
    -0.06
     herpes
    -0.06
    POSITIVE LOGITS
    _CART
    0.07
     �
    0.07
    <T
    0.06
    />.
    0.06
     Dě
    0.06
     Rout
    0.06
    xEF
    0.06
     HTTP
    0.06
    indhoven
    0.06
    BAB
    0.06
    Act Density 0.002%

    No Known Activations