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

    Neuronpedia

    INDEX
    Explanations

    code/algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .radians
    -0.08
    闪
    -0.07
     Ramadan
    -0.07
     adamant
    -0.07
     Detroit
    -0.07
    azeera
    -0.07
     holidays
    -0.07
    ’:
    -0.07
     MART
    -0.06
    .AddDays
    -0.06
    POSITIVE LOGITS
     CO
    0.07
     ARRAY
    0.07
     profound
    0.07
    ᑯ
    0.07
     P
    0.07
    tail
    0.07
     Jen
    0.07
     Unit
    0.07
     igual
    0.07
     선
    0.07
    Act Density 0.005%

    No Known Activations