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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usernames
    -0.07
    uiten
    -0.07
    .every
    -0.07
    (map
    -0.07
     バ
    -0.06
    prof
    -0.06
     evidently
    -0.06
    ich
    -0.06
     extensions
    -0.06
     conte
    -0.06
    POSITIVE LOGITS
     nth
    0.07
     작은
    0.07
    พอ
    0.06
     _
↵
    0.06
    逆
    0.06
     Chef
    0.06
     isEqual
    0.06
     대통령
    0.06
     возник
    0.06
     olur
    0.06
    Act Density 0.008%

    No Known Activations