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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ensured
    -0.06
    �
    -0.06
    _utilities
    -0.06
    “But
    -0.06
    」と
    -0.06
    505
    -0.06
    Whole
    -0.06
     Entity
    -0.06
    инув
    -0.06
    Splash
    -0.06
    POSITIVE LOGITS
     비
    0.07
     dispers
    0.07
    Mike
    0.07
     apprent
    0.06
    (mutex
    0.06
     ها
    0.06
    clidean
    0.06
     kin
    0.06
    ±n
    0.06
    сяг
    0.06
    Act Density 0.020%

    No Known Activations