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

    Neuronpedia

    INDEX
    Explanations

    MHz and GHz frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.98
    iin
    0.94
    raphic
    0.92
    ing
    0.89
    iap
    0.88
    nox
    0.87
    iad
    0.86
    in
    0.86
     for
    0.86
    ties
    0.84
    POSITIVE LOGITS
    то
    1.98
     to
    1.50
    на
    1.46
    ש
    1.42
    д
    1.37
    د
    1.34
    ل
    1.31
    و
    1.31
    ü
    1.30
    к
    1.27
    Act Density 0.005%

    No Known Activations