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

    Neuronpedia

    INDEX
    Explanations

    health risks and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ene
    0.56
    .
    0.48
    ammer
    0.47
    utes
    0.46
    ical
    0.46
     supplement
    0.46
    umni
    0.46
    eses
    0.45
    amending
    0.45
    ible
    0.45
    POSITIVE LOGITS
     பார்க்க
    0.50
     Cái
    0.50
     Piy
    0.48
     들어
    0.47
     Cere
    0.47
     ALEX
    0.47
     Khe
    0.46
     Antic
    0.46
     фараз
    0.45
     Baş
    0.44
    Act Density 0.000%

    No Known Activations