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

    Neuronpedia

    INDEX
    Explanations

    file names starting with untitled or screenshot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implementations
    0.41
     мәкалә
    0.39
    тать
    0.36
     naïve
    0.36
    maintain
    0.36
     इकाइयों
    0.36
    陘
    0.36
    abhavo
    0.35
     밖에
    0.35
    abling
    0.35
    POSITIVE LOGITS
     Untitled
    0.89
    untitled
    0.89
     untitled
    0.84
    Untitled
    0.82
    IMG
    0.73
     JPG
    0.73
     IMG
    0.73
     screenshot
    0.71
     Screenshot
    0.69
    Screenshot
    0.66
    Act Density 0.010%

    No Known Activations