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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stellen
    -0.08
    Alle
    -0.08
    ====
    -0.08
    ne
    -0.07
    NE
    -0.07
    ALLE
    -0.07
    alle
    -0.07
    inde
    -0.07
     ネ
    -0.07
     Vern
    -0.07
    POSITIVE LOGITS
    148
    0.11
    548
    0.10
    745
    0.09
    547
    0.09
    545
    0.09
    348
    0.09
    746
    0.09
    543
    0.09
    346
    0.09
    146
    0.09
    Act Density 0.130%

    No Known Activations