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

    Neuronpedia

    INDEX
    Explanations

    programming terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     em
    -0.07
    디오
    -0.06
    (tex
    -0.06
     Widgets
    -0.06
     Hotel
    -0.06
     hotel
    -0.06
     forehead
    -0.06
     font
    -0.06
    ANGUAGE
    -0.06
     Tort
    -0.06
    POSITIVE LOGITS
     debunk
    0.07
     автом
    0.07
    (clock
    0.07
     threadIdx
    0.06
     Trotsky
    0.06
     apopt
    0.06
     admirable
    0.06
     ترجمه
    0.06
     αρι
    0.06
    ขว
    0.06
    Act Density 0.111%

    No Known Activations