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

    Neuronpedia

    INDEX
    Explanations

    variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biomark
    0.45
     Ashanti
    0.45
     HTMLSc
    0.44
     knn
    0.44
     ইহাই
    0.44
    撾
    0.43
    ⊠
    0.43
     colorChoice
    0.43
    ছু
    0.43
    ahiye
    0.43
    POSITIVE LOGITS
    ef
    0.43
    ablo
    0.40
    产生
    0.37
    cluded
    0.37
     cursor
    0.37
     disabled
    0.37
     Disabled
    0.36
    fier
    0.36
    +
    0.36
    de
    0.35
    Act Density 0.001%

    No Known Activations