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

    Neuronpedia

    INDEX
    Explanations

    Mam, still, with, have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Four
    0.68
     च
    0.67
    ൊരു
    0.66
    кугӀ
    0.66
     yüzy
    0.64
     конку
    0.63
     mí
    0.63
     интеллек
    0.62
     kaise
    0.62
    ↵↵↵↵↵↵↵↵↵↵↵
    0.62
    POSITIVE LOGITS
     बताई
    0.71
    itiers
    0.69
    ይል
    0.66
    έσ
    0.66
    бва
    0.66
    Crit
    0.65
    Use
    0.64
    िली
    0.64
    Hobbies
    0.63
    வாய்
    0.63
    Act Density 0.000%

    No Known Activations