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

    Neuronpedia

    INDEX
    Explanations

    numbers in URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Liability
    0.35
    Chronic
    0.35
     Qualität
    0.34
    Tub
    0.34
     দেখিল
    0.33
    ভূমিতে
    0.33
    জিওথের
    0.33
    珽
    0.33
    ंसारी
    0.33
     responsabilité
    0.32
    POSITIVE LOGITS
    ↵
    0.57
    .
    0.54
    v
    0.52
    u
    0.47
    ,
    0.45
    ?
    0.45
    s
    0.42
    ;
    0.42
    +
    0.41
    ch
    0.41
    Act Density 0.013%

    No Known Activations