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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trauma
    -0.07
    797
    -0.07
     Quinn
    -0.06
    000
    -0.06
    construction
    -0.06
     insane
    -0.06
     convin
    -0.06
    "a
    -0.06
     управління
    -0.06
     onion
    -0.06
    POSITIVE LOGITS
     by
    0.25
     By
    0.19
     BY
    0.18
    by
    0.15
    By
    0.15
    BY
    0.14
    _by
    0.14
    _BY
    0.13
    -by
    0.12
    (By
    0.11
    Act Density 0.318%

    No Known Activations