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

    Neuronpedia

    INDEX
    Explanations

    text alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    proofing
    0.64
     proof
    0.49
    Proof
    0.45
     renovating
    0.44
    NgramModel
    0.43
     Proof
    0.43
     незавершена
    0.42
    urenc
    0.41
    proof
    0.41
    PROOF
    0.41
    POSITIVE LOGITS
     left
    1.13
     Left
    0.98
    left
    0.97
     center
    0.95
    center
    0.91
    左
    0.89
    Left
    0.88
     Center
    0.87
    Center
    0.86
     right
    0.82
    Act Density 0.007%

    No Known Activations