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

    Neuronpedia

    INDEX
    Explanations

    technical reports and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KEEP
    -0.07
    pie
    -0.07
    مود
    -0.07
    (Uri
    -0.06
    pid
    -0.06
    �
    -0.06
     wand
    -0.06
    venience
    -0.06
    cdnjs
    -0.06
     삭제
    -0.06
    POSITIVE LOGITS
    ellaneous
    0.07
    />↵↵
    0.07
     HelloWorld
    0.06
    noticed
    0.06
    .“
    0.06
    !).↵↵
    0.06
     assorted
    0.06
     отверсти
    0.06
     terminates
    0.06
    ']↵
    0.06
    Act Density 0.000%

    No Known Activations