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

    Neuronpedia

    INDEX
    Explanations

    PATH environment variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NATURE
    0.43
    飾
    0.41
     Drainage
    0.40
     তন্ম
    0.40
    packaging
    0.38
    nature
    0.38
    特性
    0.37
    包装
    0.36
     fag
    0.36
     декора
    0.35
    POSITIVE LOGITS
    wiad
    0.38
    群体
    0.38
    epine
    0.38
     antip
    0.36
     epi
    0.36
    APH
    0.36
     अल्प
    0.35
    ঙ্কের
    0.35
    turbulence
    0.35
     szervez
    0.35
    Act Density 0.004%

    No Known Activations