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

    Neuronpedia

    INDEX
    Explanations

    code and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ronaldo
    0.76
     Golpe
    0.75
     imit
    0.74
    ەد
    0.73
     melanin
    0.72
     Nickelodeon
    0.72
     Pause
    0.71
     pause
    0.71
     Firewall
    0.71
     HDL
    0.71
    POSITIVE LOGITS
    需要
    0.73
    ujah
    0.68
    rypto
    0.68
    parsed
    0.67
    iances
    0.66
     मुताब
    0.66
     যু
    0.66
    łu
    0.66
     ইন্দো
    0.65
    6
    0.64
    Act Density 0.000%

    No Known Activations