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

    Neuronpedia

    INDEX
    Explanations

    lists of concepts or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Underwater
    0.61
    Underwater
    0.55
    submarine
    0.53
    海底
    0.51
     undersea
    0.51
     underwater
    0.50
     Cable
    0.50
     подвод
    0.50
    纜
    0.50
     кабе
    0.49
    POSITIVE LOGITS
     zyg
    0.44
     Indian
    0.43
     stigma
    0.42
    ter
    0.40
     speaker
    0.40
     over
    0.40
    Assembl
    0.40
    Cardinal
    0.40
    arin
    0.40
     bald
    0.39
    Act Density 0.000%

    No Known Activations