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

    Neuronpedia

    INDEX
    Explanations

    questions and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atur
    -0.07
    utches
    -0.07
    ABB
    -0.07
    Tpl
    -0.07
    dbname
    -0.06
     morphology
    -0.06
    �
    -0.06
    ply
    -0.06
    reduce
    -0.06
     resentment
    -0.06
    POSITIVE LOGITS
     vase
    0.07
     صنع
    0.07
     torrent
    0.07
     centroid
    0.06
     rooted
    0.06
     iPad
    0.06
     dej
    0.06
    важа
    0.06
    بة
    0.06
    ]});↵
    0.06
    Act Density 0.102%

    No Known Activations