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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veracity
    0.33
     operands
    0.30
     modifiers
    0.28
     decimals
    0.27
     vorticity
    0.27
     voxel
    0.27
     rollerskates
    0.27
     parser
    0.26
     rationality
    0.26
     thorns
    0.26
    POSITIVE LOGITS
     Similarly
    0.30
     The
    0.28
     For
    0.28
    The
    0.27
    Similarly
    0.27
     Lastly
    0.26
     An
    0.26
     During
    0.26
     Также
    0.26
     If
    0.25
    Act Density 1.504%

    No Known Activations