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

    Neuronpedia

    INDEX
    Explanations

    SQL queries and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dq
    0.48
     agencies
    0.47
     electrodes
    0.45
     bureaus
    0.45
     Полу
    0.44
     मिळा
    0.44
     fouled
    0.44
     raíces
    0.43
     solução
    0.43
     líng
    0.42
    POSITIVE LOGITS
    明日
    0.49
    此类
    0.48
    արկ
    0.46
    .
    0.45
    感恩
    0.44
    纺
    0.43
    明天
    0.42
    ebok
    0.42
    禅
    0.41
    建设
    0.41
    Act Density 0.001%

    No Known Activations