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

    Neuronpedia

    INDEX
    Explanations

    fetch data, uses Tailwind, represent your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    0.48
     وإ
    0.46
     গরম
    0.45
     אם
    0.45
     عَل
    0.44
    MARY
    0.44
    ^{*}$
    0.44
     ול
    0.44
    ~\
    0.43
     і
    0.43
    POSITIVE LOGITS
     contained
    0.52
    ，
    0.52
     ru
    0.50
     ruin
    0.49
     fluent
    0.48
     zostały
    0.46
    ෂ
    0.46
     spoil
    0.45
    囦
    0.45
     monitored
    0.45
    Act Density 0.001%

    No Known Activations