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

    Neuronpedia

    INDEX
    Explanations

    type of listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تلیفون
    0.48
    Despatx
    0.48
    dai
    0.47
    achadh
    0.47
     dwRes
    0.47
    वाड़ी
    0.46
    filenames
    0.46
    kiego
    0.46
    erté
    0.45
    dni
    0.44
    POSITIVE LOGITS
     type
    0.52
     On
    0.51
    类型的
    0.50
     on
    0.49
     It
    0.49
     in
    0.47
     Type
    0.46
     Tom
    0.46
     Nanjing
    0.46
     typu
    0.45
    Act Density 0.000%

    No Known Activations