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

    Neuronpedia

    INDEX
    Explanations

    code syntax or timecodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    少
    0.71
    脫
    0.64
     შემდეგ
    0.63
    饑
    0.63
    脱
    0.57
    いわ
    0.57
    த்திற்கான
    0.57
     coups
    0.57
    插入
    0.56
    半島
    0.56
    POSITIVE LOGITS
     Rossi
    0.60
     Astana
    0.59
     Carlos
    0.58
    rektor
    0.57
    Carlos
    0.57
    Bep
    0.57
     Kotlin
    0.57
     Californian
    0.56
     स्वरुप
    0.56
     Popper
    0.56
    Act Density 0.001%

    No Known Activations