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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     half
    -0.07
    /documents
    -0.06
    arrière
    -0.06
    ὂ
    -0.06
    .newBuilder
    -0.06
    rupt
    -0.06
    莫斯
    -0.06
    䓨
    -0.06
     synt
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Beautiful
    0.07
     Sadd
    0.07
     chevy
    0.07
     مجرد
    0.07
     Inspir
    0.07
    荦
    0.07
     Seeking
    0.07
     יש
    0.07
     Harr
    0.07
    بارك
    0.06
    Act Density 0.031%

    No Known Activations