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

    Neuronpedia

    INDEX
    Explanations

    Lazarski bandwidth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ங்கிணை
    0.99
     сторону
    0.91
     primeiro
    0.88
     соответствии
    0.88
     cadrul
    0.86
     طریق
    0.85
    __.
    0.85
     accordance
    0.85
     широкий
    0.84
    в
    0.83
    POSITIVE LOGITS
    hoc
    1.05
     agony
    1.04
     insomnia
    0.97
     hops
    0.94
    痪
    0.94
     whenever
    0.93
    痛苦
    0.93
     frustrating
    0.93
     pains
    0.93
    工
    0.93
    Act Density 0.002%

    No Known Activations