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

    Neuronpedia

    INDEX
    Explanations

    setTimeout and setInterval calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Iniciar
    0.53
    ').
    0.49
    .");
    0.49
     vaccinate
    0.48
    向き
    0.47
     transact
    0.46
    .”
    0.46
     socialize
    0.46
     discredit
    0.46
    잊
    0.46
    POSITIVE LOGITS
    a
    0.76
    n
    0.75
    其他
    0.67
    u
    0.64
    i
    0.62
     algebras
    0.60
    com
    0.59
     algebra
    0.59
    it
    0.59
     alkaloids
    0.57
    Act Density 0.001%

    No Known Activations