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

    Neuronpedia

    INDEX
    Explanations

    digit identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finalized
    -0.07
    禔
    -0.07
     organize
    -0.07
    ﯧ
    -0.07
     catal
    -0.07
    䅟
    -0.07
    柰
    -0.06
    どれ
    -0.06
     liste
    -0.06
     להשתמש
    -0.06
    POSITIVE LOGITS
     backers
    0.07
    ///<
    0.07
    昆山
    0.07
     Display
    0.07
    .document
    0.07
    :<
    0.06
     backups
    0.06
    ווד
    0.06
    、“
    0.06
     //"
    0.06
    Act Density 0.002%

    No Known Activations