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

    Neuronpedia

    INDEX
    Explanations

    checks if/for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Europa
    0.41
    很难
    0.37
    Numbered
    0.37
     کھیلو
    0.36
     వీరి
    0.35
     سرد
    0.35
    sher
    0.35
    จริงๆ
    0.35
    柔
    0.35
    ファッション
    0.34
    POSITIVE LOGITS
     whether
    0.77
    是否
    0.75
     apakah
    0.73
     detect
    0.73
     detects
    0.72
     detected
    0.71
    かどうか
    0.71
    是否存在
    0.69
     detecting
    0.68
     checkFor
    0.67
    Act Density 0.317%

    No Known Activations