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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liga
    -0.07
    aturity
    -0.07
    atır
    -0.06
     commodity
    -0.06
    ASC
    -0.06
    aker
    -0.06
    화
    -0.06
    γγραφ
    -0.06
    Duplicates
    -0.06
    警
    -0.06
    POSITIVE LOGITS
    /save
    0.07
    τογραφ
    0.06
     osm
    0.06
    .idea
    0.06
    olog
    0.06
     cé
    0.06
    +"/"+
    0.06
    wnd
    0.06
     الشر
    0.06
    [train
    0.06
    Act Density 0.008%

    No Known Activations