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

    Neuronpedia

    INDEX
    Explanations

    is equal to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zem
    -0.11
    ==>
    -0.09
    è·Ŀ
    -0.09
     imap
    -0.09
    ]=>
    -0.09
     Gupta
    -0.09
    ÑĩÑĥк
    -0.09
    +=(
    -0.08
    toBeInTheDocument
    -0.08
    ='{$
    -0.08
    POSITIVE LOGITS
     equal
    0.69
    equal
    0.50
     Equal
    0.49
     equals
    0.47
     igual
    0.42
    Equal
    0.41
     ÑĢав
    0.40
     EQUAL
    0.39
    .equal
    0.36
    _equal
    0.36
    Act Density 0.135%

    No Known Activations