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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     马
    -0.06
     Marxist
    -0.06
     Rank
    -0.06
     Fritz
    -0.06
    _SIGNAL
    -0.06
    (expression
    -0.06
     simples
    -0.06
     FIN
    -0.06
    _notice
    -0.05
    -en
    -0.05
    POSITIVE LOGITS
    "]↵↵
    0.08
    avenous
    0.07
    _PRIVATE
    0.07
    ,”
    0.07
     ="
    0.07
    ”
    0.07
    imensional
    0.06
    .']
    0.06
    iou
    0.06
    ToolStripMenuItem
    0.06
    Act Density 0.000%

    No Known Activations