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

    Neuronpedia

    INDEX
    Explanations

    characteristics of viruses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.55
     donation
    0.48
     manifold
    0.48
     chaf
    0.47
     membrane
    0.46
     thump
    0.45
     puncture
    0.45
     harsher
    0.45
     lunch
    0.45
     resignation
    0.45
    POSITIVE LOGITS
    ajo
    0.45
    飽
    0.45
    ঃ
    0.44
    Чер
    0.44
    ißler
    0.44
     தெய்
    0.44
    Одна
    0.44
    $-$,
    0.43
    ay
    0.42
    сан
    0.42
    Act Density 0.005%

    No Known Activations