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

    Neuronpedia

    INDEX
    Explanations

    type Output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    释放
    0.43
    peicher
    0.41
    generate
    0.40
    Generate
    0.40
    상을
    0.38
    ibor
    0.38
    釋
    0.38
    usetzen
    0.38
    არის
    0.38
    기를
    0.37
    POSITIVE LOGITS
     excelled
    0.41
     विक
    0.40
     subscribers
    0.38
     pumped
    0.38
     swing
    0.38
     swings
    0.37
     Swing
    0.37
     Ivory
    0.36
     Meade
    0.36
     telescopes
    0.36
    Act Density 0.000%

    No Known Activations