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

    Neuronpedia

    INDEX
    Explanations

    running on servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Approved
    0.40
     conditioners
    0.38
     tails
    0.38
     exame
    0.38
     chromospheres
    0.37
    partials
    0.37
    ="../../../../
    0.37
     examiners
    0.37
     cabinetry
    0.36
    一声
    0.36
    POSITIVE LOGITS
    武
    0.49
    setVisible
    0.45
     MUSIC
    0.43
    﨑
    0.40
    踰
    0.40
    渡
    0.40
     пише
    0.39
    陽
    0.38
     OWNER
    0.38
    曰
    0.37
    Act Density 0.000%

    No Known Activations