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

    Neuronpedia

    INDEX
    Explanations

    Excel, settings, add

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    صاب
    0.49
     asigur
    0.47
     ornate
    0.47
    ن
    0.44
     паро
    0.43
     borr
    0.42
    src
    0.42
     VAS
    0.42
    رك
    0.42
     Parce
    0.42
    POSITIVE LOGITS
    ddar
    0.46
    🥊
    0.45
    映
    0.44
    inos
    0.42
    偵
    0.41
     झेल
    0.41
    iswa
    0.40
    を通じて
    0.40
    dling
    0.39
     tomatoes
    0.39
    Act Density 0.000%

    No Known Activations