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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emore
    -1.20
    urement
    -1.19
    jących
    -1.12
     from
    -1.10
     Möglich
    -1.09
    ductors
    -1.08
    rawn
    -1.08
    yship
    -1.08
    ograft
    -1.06
    cising
    -1.00
    POSITIVE LOGITS
    }$-
    2.30
    )$-
    1.38
    $-
    1.37
    "-
    1.34
    ”-
    1.27
    “-
    1.25
    -
    1.19
    '-
    1.16
    )-
    1.16
    ’-
    1.11
    Act Density 0.068%

    No Known Activations