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

    Neuronpedia

    INDEX
    Explanations

    purpose and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.47
    Gun
    0.46
    ض
    0.46
    Gün
    0.46
    ش
    0.45
    ل
    0.45
    स्ट
    0.44
     ainult
    0.44
     egiten
    0.43
    Dir
    0.43
    POSITIVE LOGITS
    gener
    0.56
     паци
    0.54
     gener
    0.52
    reactor
    0.50
     rmse
    0.48
     сухо
    0.47
     思っ
    0.47
     REACTORS
    0.46
    signale
    0.46
    ώσεις
    0.46
    Act Density 0.000%

    No Known Activations