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

    Neuronpedia

    INDEX
    Explanations

    capability, cycle, varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roosevelt
    0.49
     residential
    0.47
     pursuant
    0.46
    াপিত
    0.46
    ).-
    0.46
     kommen
    0.46
     Bikini
    0.46
     comprise
    0.45
     mercredi
    0.45
     reliably
    0.45
    POSITIVE LOGITS
    一丝
    0.55
    ments
    0.54
    ng
    0.52
    k
    0.50
    ق
    0.47
    ว่าง
    0.47
    ty
    0.46
    sed
    0.46
    س
    0.45
    𝙢
    0.45
    Act Density 0.000%

    No Known Activations