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

    Neuronpedia

    INDEX
    Explanations

    security group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐠
    0.48
    ই
    0.48
    ządz
    0.48
     smashed
    0.47
     refreshments
    0.47
    ❯
    0.46
    何の
    0.46
    ام
    0.46
     sorely
    0.45
     Faites
    0.45
    POSITIVE LOGITS
    ch
    0.44
    chit
    0.37
    f
    0.37
    wid
    0.34
    rooms
    0.34
    bath
    0.33
    Score
    0.33
    database
    0.33
     виправи
    0.33
    gmail
    0.33
    Act Density 0.003%

    No Known Activations