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

    Neuronpedia

    INDEX
    Explanations

    amniotic fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logarithms
    0.91
     logarithmic
    0.76
    Log
    0.74
     Logos
    0.69
    Polynomial
    0.69
    \;
    0.66
     logarithm
    0.66
    Dee
    0.63
    Palindrome
    0.63
     Gespräch
    0.62
    POSITIVE LOGITS
    期の
    0.88
     leaped
    0.88
     improb
    0.83
    letti
    0.81
     leapt
    0.81
     irres
    0.77
     burst
    0.77
    ឯ
    0.76
     underwhelming
    0.75
     announce
    0.75
    Act Density 0.002%

    No Known Activations