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

    Neuronpedia

    INDEX
    Explanations

    think you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.50
     দল
    0.48
     Tämä
    0.47
     দেয়
    0.47
    ários
    0.46
    ando
    0.45
    alahan
    0.45
     פ
    0.45
    Avro
    0.45
     ប្រ
    0.44
    POSITIVE LOGITS
     cláus
    0.46
     claust
    0.46
     every
    0.45
     overcrowded
    0.44
     repeatedly
    0.44
    on
    0.43
     mesmer
    0.43
     exactly
    0.43
    ビッグ
    0.43
     inexplicable
    0.43
    Act Density 0.002%

    No Known Activations