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

    Neuronpedia

    INDEX
    Explanations

    famously, reportedly, allegedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Recently
    0.95
     Recently
    0.93
     Now
    0.91
    पिछले
    0.88
     recent
    0.87
     گزشتہ
    0.85
     bisher
    0.85
     recente
    0.85
    Now
    0.84
     আপাতত
    0.84
    POSITIVE LOGITS
     famously
    1.54
     knew
    1.46
     reportedly
    1.45
     lived
    1.43
     sought
    1.40
     believed
    1.38
     disliked
    1.32
     relied
    1.32
     longed
    1.27
     allegedly
    1.27
    Act Density 0.117%

    No Known Activations