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

    Neuronpedia

    INDEX
    Explanations

    helpful if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कडील
    0.42
    idade
    0.40
     bahwa
    0.39
     omt
    0.37
     ہل
    0.37
    డంతో
    0.37
    фин
    0.36
    า
    0.36
    ление
    0.35
    ว่า
    0.34
    POSITIVE LOGITS
     to
    0.47
     furious
    0.46
     laughed
    0.44
     तुम्
    0.44
     तुम्हें
    0.44
     fished
    0.41
     chanted
    0.41
     እየሱስ
    0.40
     liberating
    0.40
     INFORMATION
    0.40
    Act Density 0.001%

    No Known Activations