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

    Neuronpedia

    INDEX
    Explanations

    intelligence model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downtown
    0.43
    gazebo
    0.42
    看板
    0.41
    Рабо
    0.40
    ื้อง
    0.40
    ሆ
    0.40
     название
    0.39
     проє
    0.39
     Рабо
    0.39
    巌
    0.39
    POSITIVE LOGITS
    циями
    0.38
     Coefficient
    0.38
     reconciled
    0.37
     overwhelmed
    0.37
     autop
    0.37
    ختی
    0.37
    ="{{
    0.36
     overpower
    0.36
    voluntary
    0.36
    毛
    0.35
    Act Density 0.001%

    No Known Activations