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

    Neuronpedia

    INDEX
    Explanations

    entity performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inoltre
    1.32
     ayrıca
    1.17
     tedy
    1.08
     quindi
    1.04
     egyéb
    1.03
     tehát
    1.03
     então
    1.03
     아직
    1.02
    뿐
    1.01
     অবশ্য
    0.99
    POSITIVE LOGITS
    рома
    0.74
    ™
    0.71
    intosh
    0.70
     Himalayan
    0.68
    man
    0.67
    ®
    0.64
    <0xA5>
    0.62
    en
    0.62
    improv
    0.60
    を実現
    0.59
    Act Density 0.024%

    No Known Activations