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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	expect
    -0.07
     Pocket
    -0.07
     PDT
    -0.07
    Todd
    -0.06
     Todd
    -0.06
    ули
    -0.06
    sta
    -0.06
     Allow
    -0.06
    Seen
    -0.06
     PRIVATE
    -0.06
    POSITIVE LOGITS
    ในว
    0.07
    __;
    0.07
     ihnen
    0.06
    OwnProperty
    0.06
     toll
    0.06
    ्रक
    0.06
     中
    0.06
     Jub
    0.06
    _fe
    0.06
    +-+-+-+-+-+-+-+-
    0.06
    Act Density 0.039%

    No Known Activations