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

    Neuronpedia

    INDEX
    Explanations

    responding to "asked"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    塭
    0.46
     ระบบ
    0.45
     aufgrund
    0.45
     estoque
    0.44
     skutecz
    0.43
     تلق
    0.43
     однозна
    0.43
     פון
    0.43
    𝐂
    0.43
     sicher
    0.42
    POSITIVE LOGITS
    h
    0.47
    butanol
    0.43
    ken
    0.38
    deprecated
    0.38
    ß
    0.38
     variation
    0.38
    else
    0.38
    ih
    0.37
    inj
    0.37
    different
    0.36
    Act Density 0.003%

    No Known Activations