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

    Neuronpedia

    INDEX
    Explanations

    say ending with 89

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    798
    -0.13
    398
    -0.12
    796
    -0.12
    797
    -0.12
    397
    -0.12
    598
    -0.12
    297
    -0.12
    497
    -0.11
    998
    -0.11
    597
    -0.11
    POSITIVE LOGITS
    889
    0.20
    189
    0.19
    689
    0.18
    709
    0.17
    089
    0.17
    289
    0.16
    909
    0.16
    789
    0.16
    489
    0.16
    509
    0.16
    Act Density 0.238%

    No Known Activations