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

    Neuronpedia

    INDEX
    Explanations

    beginning of string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loglevel
    0.37
     logging
    0.34
    த்து
    0.34
     عليكم
    0.33
    itatea
    0.33
     معكم
    0.33
    otransfer
    0.33
    цю
    0.32
    ikler
    0.32
     settling
    0.32
    POSITIVE LOGITS
     ú
    0.35
     jul
    0.34
     Untitled
    0.34
     blockade
    0.33
     bar
    0.33
    యిత
    0.32
     myBuilder
    0.32
     blok
    0.32
     uniq
    0.32
     Genes
    0.32
    Act Density 0.003%

    No Known Activations