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

    Neuronpedia

    INDEX
    Explanations

    to make a file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    0.52
     của
    0.51
    Лі
    0.50
     bhavanti
    0.50
    subequations
    0.49
    亅
    0.49
    tragung
    0.48
    n
    0.47
    वतात
    0.47
    Mình
    0.47
    POSITIVE LOGITS
    oli
    0.48
    onents
    0.46
    ot
    0.46
     confident
    0.45
     cracking
    0.45
     KeyError
    0.45
    overs
    0.44
    uly
    0.44
    uba
    0.44
    uk
    0.44
    Act Density 0.000%

    No Known Activations