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

    Neuronpedia

    INDEX
    Explanations

    people, professions, and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    1.02
    t
    0.99
    audi
    0.96
    atrical
    0.95
    з
    0.92
     keseluruhan
    0.91
    lma
    0.90
    ts
    0.90
    humidity
    0.90
    y
    0.89
    POSITIVE LOGITS
    $.\\
    1.10
    再次
    1.10
     onClose
    1.02
     že
    1.01
     paramedics
    1.00
    刺繍
    0.99
     reiterated
    0.98
     worsened
    0.97
    友
    0.97
     đoàn
    0.96
    Act Density 0.047%

    No Known Activations