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

    Neuronpedia

    INDEX
    Explanations

    merchant, database, teacher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fixe
    0.44
     prepar
    0.42
    тай
    0.42
     operativos
    0.42
     ouvre
    0.42
    යක්
    0.41
     raza
    0.41
     cytoskeleton
    0.41
     ouv
    0.40
     Picker
    0.40
    POSITIVE LOGITS
    IMA
    0.50
    sourceIP
    0.46
    lja
    0.46
     bọn
    0.45
    riminal
    0.45
    äller
    0.45
    urup
    0.43
    dct
    0.43
    éli
    0.43
    itudini
    0.43
    Act Density 0.001%

    No Known Activations