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

    Neuronpedia

    INDEX
    Explanations

    condition when or if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чтобы
    0.49
     щоб
    0.46
     જેથી
    0.44
     чтоб
    0.44
    herst
    0.43
     대신
    0.43
    Чтобы
    0.43
    য়োজনীয়
    0.42
     instead
    0.42
    merken
    0.41
    POSITIVE LOGITS
     cuando
    0.64
     عندما
    0.61
     when
    0.60
    when
    0.59
     quando
    0.58
     Properly
    0.55
     properly
    0.53
     certain
    0.52
     когда
    0.52
     když
    0.52
    Act Density 0.199%

    No Known Activations