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

    Neuronpedia

    INDEX
    Explanations

    particularly in technical domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MovementControls
    0.44
    enchymal
    0.41
    ámico
    0.41
    ρει
    0.41
    ந்த
    0.41
    ন্তী
    0.40
    quels
    0.40
     collaboratively
    0.40
    нике
    0.40
    ደጋ
    0.40
    POSITIVE LOGITS
    ayat
    0.49
    AY
    0.47
    dal
    0.46
    NA
    0.46
    Ä
    0.45
    dan
    0.44
    Languages
    0.44
    Remember
    0.44
    Foreign
    0.43
    **.
    0.43
    Act Density 0.000%

    No Known Activations