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

    Neuronpedia

    INDEX
    Explanations

    model starts response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depends
    0.39
     only
    0.38
     not
    0.38
     depend
    0.36
     it
    0.35
     said
    0.34
     but
    0.32
     repetitions
    0.31
     others
    0.31
     aber
    0.31
    POSITIVE LOGITS
    geoning
    0.40
    Selamat
    0.39
    reetings
    0.39
    ECUTIVE
    0.39
     ऑस्ट्रेलियाई
    0.39
    ቅ
    0.39
    undering
    0.37
     Сьогодні
    0.36
    ANSAS
    0.36
     새로운
    0.36
    Act Density 0.107%

    No Known Activations