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

    Neuronpedia

    INDEX
    Explanations

    substitute into the equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করলেও
    0.47
    ÑO
    0.46
    žky
    0.44
    Percentages
    0.43
     মাল
    0.43
    츈
    0.43
    穼
    0.43
    ractical
    0.42
    ^{\#}\
    0.42
    荪
    0.42
    POSITIVE LOGITS
     countenance
    0.44
     Lucas
    0.43
     Seeking
    0.41
     be
    0.41
     luck
    0.41
     its
    0.40
     seeking
    0.40
     seek
    0.40
     run
    0.39
     match
    0.39
    Act Density 0.004%

    No Known Activations