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

    Neuronpedia

    INDEX
    Explanations

    alter table sql commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絴
    0.67
    😚
    0.66
    জ
    0.65
     :/
    0.65
     റ
    0.61
    ঁর
    0.61
     nt
    0.60
     aynı
    0.59
     että
    0.59
    많
    0.59
    POSITIVE LOGITS
    ного
    0.70
    Session
    0.63
    et
    0.62
    messer
    0.59
    Runtime
    0.58
    during
    0.58
    Package
    0.57
    Timestamp
    0.57
    Airport
    0.56
    ת
    0.56
    Act Density 0.000%

    No Known Activations