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

    Neuronpedia

    INDEX
    Explanations

    los cuales / each of which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sort
    -0.15
     neboť
    -0.10
    :::::::::
    -0.09
     ať
    -0.09
     takže
    -0.09
    (where
    -0.09
     kdo
    -0.09
     pÅĻiÄįemž
    -0.08
    displayText
    -0.08
     jaké
    -0.08
    POSITIVE LOGITS
     which
    0.64
    which
    0.54
     Which
    0.48
    Which
    0.47
     whom
    0.46
     cui
    0.46
     WHICH
    0.44
     коÑĤоÑĢÑĭÑħ
    0.44
     οÏĢοία
    0.43
     коÑĤоÑĢого
    0.42
    Act Density 0.220%

    No Known Activations