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

    Neuronpedia

    INDEX
    Explanations

    contemporary emissions regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kolom
    0.43
     venire
    0.42
     खड
    0.41
    configurations
    0.41
    Column
    0.40
    stack
    0.39
     Mur
    0.38
    தியின்
    0.38
    цами
    0.38
    寇
    0.38
    POSITIVE LOGITS
    ]])
    0.41
     beli
    0.39
     オーバー
    0.38
     হামিদ
    0.38
    PHONE
    0.37
     થી
    0.37
    年后
    0.37
    ]].
    0.36
    PERATURE
    0.36
    食べた
    0.36
    Act Density 0.000%

    No Known Activations