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
     heaven
    -0.07
     Mao
    -0.07
    495
    -0.07
    18
    -0.07
    17
    -0.07
     द
    -0.07
    15
    -0.07
    ao
    -0.07
     ct
    -0.06
    475
    -0.06
    POSITIVE LOGITS
     elapsedTime
    0.08
     Krist
    0.07
    Allow
    0.07
    +z
    0.07
    _Stop
    0.06
     Viet
    0.06
    ()
    0.06
     Comes
    0.06
    #######↵
    0.06
     exposes
    0.06
    Act Density 0.015%

    No Known Activations