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

    Neuronpedia

    INDEX
    Explanations

    actually belonged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کو
    0.47
     pronta
    0.45
     everytime
    0.45
     команд
    0.44
     liberar
    0.44
     awalnya
    0.44
    ک
    0.44
     rapidement
    0.43
     wanneer
    0.43
     shorthand
    0.42
    POSITIVE LOGITS
     bicycl
    0.45
     distinctly
    0.43
     bicycle
    0.42
     drawn
    0.42
     deleterious
    0.42
     shower
    0.42
     disturbing
    0.42
     deteriorated
    0.41
     disturb
    0.41
    oub
    0.41
    Act Density 0.002%

    No Known Activations