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

    Neuronpedia

    INDEX
    Explanations

    the followed by a concluding noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.54
     volcanoes
    0.53
     soldats
    0.53
     aurait
    0.52
     it
    0.50
     auraient
    0.50
     musik
    0.49
     spores
    0.47
     effets
    0.47
     avez
    0.47
    POSITIVE LOGITS
    ↵
    0.69
    -
    0.67
    EN
    0.54
    AN
    0.53
    Timeout
    0.53
    p
    0.52
    ON
    0.50
    en
    0.49
    NA
    0.48
    6
    0.47
    Act Density 0.031%

    No Known Activations