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

    Neuronpedia

    INDEX
    Explanations

    code examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以在
    0.42
     implant
    0.40
    GFR
    0.40
     prevent
    0.40
    ,
    0.40
     quen
    0.39
     soma
    0.39
    univers
    0.39
    })$
    0.38
    grass
    0.38
    POSITIVE LOGITS
    婹
    0.46
    委会
    0.46
    นี
    0.45
     मैचों
    0.43
    лися
    0.42
    нат
    0.42
    仩
    0.42
    лася
    0.42
    ेशनों
    0.42
    缉
    0.41
    Act Density 0.001%

    No Known Activations