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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qed
    -0.08
    	reset
    -0.07
    eno
    -0.07
     implement
    -0.07
     executing
    -0.07
    uchen
    -0.07
     rn
    -0.07
    into
    -0.07
     [])
    -0.07
    automation
    -0.06
    POSITIVE LOGITS
    မ
    0.07
    亲人
    0.07
    转折
    0.07
    -map
    0.07
    Timing
    0.06
    ↵
    0.06
     الصحفي
    0.06
    TableWidgetItem
    0.06
     NX
    0.06
    ﺆ
    0.06
    Act Density 0.034%

    No Known Activations