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

    Neuronpedia

    INDEX
    Explanations

    HT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pdf
    -0.07
     obvious
    -0.06
    orph
    -0.06
     theaters
    -0.06
     своих
    -0.06
     extreme
    -0.06
     최근
    -0.06
    Pwd
    -0.06
     deserve
    -0.06
     sebou
    -0.06
    POSITIVE LOGITS
     Hicks
    0.07
     네이트
    0.07
     Τα
    0.06
    }(
    0.06
    “↵↵
    0.06
     fieldType
    0.06
     hog
    0.06
     tutar
    0.06
     getch
    0.06
    ñana
    0.06
    Act Density 0.005%

    No Known Activations