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

    Neuronpedia

    INDEX
    Explanations

    malloc(sizeof(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সালে
    1.22
     aficionados
    1.12
     Leibn
    1.11
     berapa
    1.11
     дней
    1.08
     إدارة
    1.08
     திட
    1.07
     liczb
    1.05
     acordo
    1.04
    embangan
    1.03
    POSITIVE LOGITS
    ened
    0.99
    ntilde
    0.99
    म
    0.96
    erves
    0.96
    <td>
    0.95
    criptions
    0.95
    ان
    0.94
    ../../
    0.92
    am
    0.91
    :],
    0.91
    Act Density 0.003%

    No Known Activations