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

    Neuronpedia

    INDEX
    Explanations

    different items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ext
    -0.07
     Ext
    -0.07
     ECS
    -0.06
    wcs
    -0.06
    好
    -0.06
    Loop
    -0.06
    だよ
    -0.06
     Metric
    -0.06
    box
    -0.06
     metric
    -0.06
    POSITIVE LOGITS
    grese
    0.07
    eni
    0.07
     uvol
    0.07
    imens
    0.07
     plead
    0.07
    te
    0.06
     bankruptcy
    0.06
    rafted
    0.06
    vement
    0.06
    ighb
    0.06
    Act Density 0.010%

    No Known Activations