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

    Neuronpedia

    INDEX
    Explanations

    highest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ma
    -0.07
     mel
    -0.06
     Ye
    -0.06
    .Label
    -0.06
    \)
    -0.06
    pac
    -0.06
    ु
    -0.06
    ंजन
    -0.06
     bu
    -0.06
     mat
    -0.06
    POSITIVE LOGITS
     дос
    0.07
     Heading
    0.07
     Invisible
    0.07
    .fname
    0.07
    หลด
    0.07
    TreeView
    0.07
     |:
    0.06
    ][:
    0.06
    (bg
    0.06
     Http
    0.06
    Act Density 0.007%

    No Known Activations