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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iniciativas
    0.40
    हिंद
    0.40
    kc
    0.39
    ዶች
    0.39
    ímenes
    0.39
     datum
    0.38
     haste
    0.37
    ꯁ
    0.37
     incite
    0.36
     déten
    0.36
    POSITIVE LOGITS
     technique
    0.80
     Technique
    0.70
     applied
    0.70
     TECHNI
    0.64
     aplicado
    0.64
     operator
    0.63
     performed
    0.61
     appliquée
    0.61
     işlemi
    0.61
     algorithm
    0.59
    Act Density 0.062%

    No Known Activations