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

    Neuronpedia

    INDEX
    Explanations

    credit card

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spiking
    0.44
     reproduction
    0.39
     shaving
    0.39
     Scaling
    0.38
     APPEND
    0.37
    ভ্র
    0.37
     机
    0.37
     Spike
    0.36
     एल्
    0.36
    ર્ટ
    0.36
    POSITIVE LOGITS
     parserOptions
    0.43
    Jimmy
    0.43
     Jimmy
    0.42
    ジ
    0.42
     azi
    0.41
     JIM
    0.41
    jim
    0.39
    höhe
    0.39
    通知
    0.39
    JIM
    0.38
    Act Density 0.038%

    No Known Activations