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

    Neuronpedia

    INDEX
    Explanations

    historical texts and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xC2>
    0.62
      
    0.60
     e
    0.56
     repeatedly
    0.54
    ´
    0.52
     "
    0.51
     ​​
    0.50
    －
    0.47
    b
    0.47
    s
    0.47
    POSITIVE LOGITS
    .!
    0.98
    !
    0.93
     Histoire
    0.89
     Understanding
    0.83
    ؟!
    0.83
    Histoire
    0.81
     Memoirs
    0.81
    .?
    0.78
    ?
    0.78
    Understanding
    0.77
    Act Density 0.000%

    No Known Activations