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

    Neuronpedia

    INDEX
    Explanations

    equals sign ("=")

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malfunction
    -0.07
    ;top
    -0.07
    玲
    -0.07
    ROTO
    -0.07
     Lyon
    -0.06
     helper
    -0.06
     CALLBACK
    -0.06
    IMO
    -0.06
    (str
    -0.06
    Pixels
    -0.06
    POSITIVE LOGITS
    954
    0.07
     Exercise
    0.07
    =forms
    0.06
    372
    0.06
    Gab
    0.06
    472
    0.06
    514
    0.06
    １０
    0.06
    502
    0.06
    �璃
    0.06
    Act Density 0.000%

    No Known Activations