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

    Neuronpedia

    INDEX
    Explanations

    referred to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Javascript
    -0.86
    espn
    -0.85
     మరి
    -0.84
     Ecole
    -0.84
    եւ
    -0.84
     frightening
    -0.84
     angka
    -0.83
    schrank
    -0.83
     Uniwersyte
    -0.82
    Друзья
    -0.81
    POSITIVE LOGITS
    <table>
    1.52
    <sup>
    1.49
     ${\
    1.13
    </th>
    1.05
    Template
    1.04
    <h3>
    0.98
    hor
    0.98
    ٔ
    0.96
    ec
    0.96
    ${\
    0.93
    Act Density 0.002%

    No Known Activations