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

    Neuronpedia

    INDEX
    Explanations

    length of the train

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     backstory
    0.91
     Navajo
    0.90
     skinny
    0.86
     Pellegr
    0.85
     comedic
    0.83
    こな
    0.82
     overly
    0.82
     chcete
    0.82
     lackluster
    0.80
     gosh
    0.79
    POSITIVE LOGITS
    cosec
    1.07
     CBSE
    1.04
    Assertion
    1.02
     formulae
    1.01
    ₹
    1.00
    <0xD5>
    1.00
     Hence
    0.99
    Hence
    0.98
     atleast
    0.97
     delhi
    0.96
    Act Density 0.182%

    No Known Activations