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

    Neuronpedia

    INDEX
    Explanations

    introducing reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pretože
    0.41
    Because
    0.37
    Which
    0.37
    them
    0.37
     Поэтому
    0.37
    Porque
    0.37
    nPlease
    0.36
    Following
    0.36
     něj
    0.36
    Therefore
    0.35
    POSITIVE LOGITS
     of
    0.72
     unlike
    0.60
     otherwise
    0.57
     obviously
    0.55
     frankly
    0.55
     technically
    0.52
     presumably
    0.52
     although
    0.52
     there
    0.51
     ultimately
    0.50
    Act Density 0.038%

    No Known Activations