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

    Neuronpedia

    INDEX
    Explanations

    numbers and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    One
    0.88
     One
    0.82
    amani
    0.78
     one
    0.77
    拂
    0.76
     blouses
    0.71
     ১০০
    0.70
    ১
    0.68
     பொரு
    0.68
     स्टोरी
    0.66
    POSITIVE LOGITS
     thirteen
    0.79
     fifteen
    0.77
     fourteen
    0.74
     fifteenth
    0.73
    十六
    0.71
     sixteen
    0.70
     eighteen
    0.69
     fourteenth
    0.69
     eighteenth
    0.67
    十八
    0.66
    Act Density 0.255%

    No Known Activations