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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espírito
    0.39
    その他の
    0.38
     grandes
    0.38
     uneasy
    0.37
     idée
    0.36
     आध्यात्मिक
    0.36
    非常に
    0.35
     libertà
    0.35
    ध्यात्म
    0.35
     Staphylococcus
    0.35
    POSITIVE LOGITS
    _
    0.68
    \_
    0.45
    -
    0.42
    elen
    0.36
    ា
    0.34
    .
    0.33
    ηση
    0.32
    queue
    0.31
    izando
    0.31
    ᴇ
    0.30
    Act Density 0.179%

    No Known Activations