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

    Neuronpedia

    INDEX
    Explanations

    Halloween and Easter activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    2.09
    де
    2.02
    ک
    1.91
    ς
    1.90
    <0x80>
    1.89
    ों
    1.75
    ク
    1.71
    от
    1.66
    ة
    1.65
    Usuario
    1.63
    POSITIVE LOGITS
    an
    1.95
     varic
    1.69
     seria
    1.63
    soever
    1.63
    am
    1.62
     DHCP
    1.59
     DAB
    1.59
     Dino
    1.58
    ﺭ
    1.57
    on
    1.56
    Act Density 0.001%

    No Known Activations