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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Copyright
    0.85
    [...]
    0.76
    http
    0.74
    https
    0.72
    How
    0.70
    <%@
    0.66
    ©
    0.66
    }]},
    0.66
    copyright
    0.65
    Than
    0.65
    POSITIVE LOGITS
     com
    1.46
     ”.
    1.46
     )
    1.41
     .”
    1.41
     ”
    1.27
     .)
    1.23
     none
    1.20
     ."
    1.13
     .
    1.10
     ’
    1.10
    Act Density 0.009%

    No Known Activations