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

    Neuronpedia

    INDEX
    Explanations

    adjective preceding noun/concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrondie
    0.43
     isEmpty
    0.42
    ంచరీలు
    0.42
     அமிலம்
    0.41
    ینګ
    0.41
     zarówno
    0.41
    ována
    0.40
    کومت
    0.39
    prüsü
    0.39
    liono
    0.39
    POSITIVE LOGITS
    -
    0.91
    _
    0.68
    ‐
    0.65
    ’
    0.64
    ­
    0.47
    0.47
    '
    0.46
    ‑
    0.44
    
    0.43
    –
    0.42
    Act Density 0.371%

    No Known Activations