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

    Neuronpedia

    INDEX
    Explanations

    Rocky Linux, Mountain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гляд
    0.45
    唃
    0.43
    学家
    0.42
     জেট
    0.41
    માન્ય
    0.41
    सूर्
    0.40
    0.40
     জল
    0.40
    Bahn
    0.40
    麦
    0.40
    POSITIVE LOGITS
     shores
    0.44
     construction
    0.39
     cr
    0.38
     shore
    0.37
     compositions
    0.37
     constructing
    0.37
    ly
    0.36
     tenacity
    0.36
     road
    0.36
     clap
    0.35
    Act Density 0.003%

    No Known Activations