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

    Neuronpedia

    INDEX
    Explanations

    No tokens, cannot make any guesses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expulsion
    -0.07
    Putting
    -0.06
    Scenario
    -0.06
     colonization
    -0.06
     وكان
    -0.06
     Bike
    -0.06
     halt
    -0.06
    �
    -0.06
     pudo
    -0.06
    ㇽ
    -0.06
    POSITIVE LOGITS
    ex
    0.08
    ("
    0.07
     analogous
    0.07
     أف
    0.07
    厍
    0.07
    ≜
    0.07
    magic
    0.07
     generate
    0.07
    (USER
    0.07
    恋
    0.07
    Act Density 0.019%

    No Known Activations