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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }}-
    0.90
     Mango
    0.83
     Zelensky
    0.80
     Spade
    0.76
     gauss
    0.76
    }^{*}=
    0.76
    }^{*}-
    0.75
     Faust
    0.74
    "],[
    0.74
     "=
    0.74
    POSITIVE LOGITS
    (\
    2.20
     (\
    2.05
    }(\
    1.86
     $(\
    1.82
    $(\
    1.75
    )(\
    1.72
    -\
    1.72
    =\
    1.70
    +\
    1.61
    <\
    1.59
    Act Density 0.116%

    No Known Activations