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

    Neuronpedia

    INDEX
    Explanations

    numbers and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ânia
    0.50
    િજા
    0.49
    ânico
    0.46
    utico
    0.46
    টিয়
    0.46
    तिरिक्त
    0.45
    andosi
    0.45
    ahaan
    0.45
    abhavo
    0.44
    Antae
    0.44
    POSITIVE LOGITS
     XOR
    0.45
     ,
    0.43
     という
    0.43
     Corruption
    0.42
    0
    0.41
    6
    0.40
    ،
    0.40
     corr
    0.39
    ੇ
    0.39
     را
    0.39
    Act Density 0.007%

    No Known Activations