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

    Neuronpedia

    INDEX
    Explanations

    tone and sharing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seits
    0.43
    ло
    0.40
    housing
    0.40
     nebo
    0.39
    ফিকুল
    0.39
     berarti
    0.38
     streetlight
    0.38
    似的
    0.38
    のでしょうか
    0.38
     oppure
    0.38
    POSITIVE LOGITS
     alkyl
    0.42
     Mummy
    0.41
    Nowadays
    0.41
     aristocracy
    0.39
    ott
    0.38
     ch
    0.38
     nông
    0.38
     Secret
    0.37
    ické
    0.37
     Nowadays
    0.37
    Act Density 0.001%

    No Known Activations