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

    Neuronpedia

    INDEX
    Explanations

    Establishing as a leader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecz
    -0.07
     as
    -0.07
     preceding
    -0.06
     다운받기
    -0.06
    .pres
    -0.06
    .slf
    -0.06
    кап
    -0.06
    ELEMENT
    -0.06
    Lang
    -0.06
     cliffs
    -0.06
    POSITIVE LOGITS
    .orange
    0.07
    _Menu
    0.07
     Baba
    0.07
     sext
    0.06
    Feed
    0.06
    /Library
    0.06
     charger
    0.06
    enance
    0.06
    Mari
    0.06
    _dark
    0.06
    Act Density 0.033%

    No Known Activations