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

    Neuronpedia

    INDEX
    Explanations

    testing and assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    histo
    0.40
     Horus
    0.38
    䂙
    0.38
    ហេ
    0.38
    эй
    0.38
    RD
    0.37
    庾
    0.37
    nomes
    0.37
     முழுக்க
    0.36
    kowo
    0.36
    POSITIVE LOGITS
    Instrumentation
    0.54
    filters
    0.53
     extinguish
    0.50
     platform
    0.49
    rule
    0.49
     rule
    0.49
     extingu
    0.47
    ext
    0.47
     filters
    0.46
     filtered
    0.46
    Act Density 0.000%

    No Known Activations