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

    Neuronpedia

    INDEX
    Explanations

    determiners and pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isc
    -0.07
    Nice
    -0.07
    _passed
    -0.06
     transformer
    -0.06
     getir
    -0.06
    ｭ
    -0.06
    Protect
    -0.06
    >Please
    -0.06
    points
    -0.06
     SC
    -0.06
    POSITIVE LOGITS
     drafted
    0.06
    rending
    0.06
     Bak
    0.06
     envisioned
    0.06
     chose
    0.06
    getToken
    0.06
    -bel
    0.06
     comprised
    0.06
     commonly
    0.06
    前に
    0.06
    Act Density 0.052%

    No Known Activations