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

    Neuronpedia

    INDEX
    Explanations

    offering further explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     please
    0.88
     ovom
    0.85
     diese
    0.79
     !!,
    0.79
     ,
    0.79
     esta
    0.75
     this
    0.75
     pension
    0.75
     conform
    0.74
     !,
    0.74
    POSITIVE LOGITS
    However
    1.10
    Example
    1.10
    Edit
    1.09
    Alternatively
    1.07
    Anyway
    1.07
    Basically
    1.07
    Of
    1.04
    Examples
    1.03
    Say
    0.98
    倒是
    0.97
    Act Density 0.299%

    No Known Activations