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

    Neuronpedia

    INDEX
    Explanations

    drug trade, RNAs, addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     edited
    0.38
     সহায়
    0.38
    ід
    0.37
    acak
    0.37
     speaking
    0.36
     juga
    0.36
    awarkan
    0.35
    enga
    0.35
     également
    0.35
     конферен
    0.35
    POSITIVE LOGITS
     amigas
    0.49
    इये
    0.46
    🍍
    0.46
     anillos
    0.44
    #
    0.44
     anillo
    0.43
    avacak
    0.42
     introns
    0.42
    Lowest
    0.41
    ♾
    0.40
    Act Density 0.000%

    No Known Activations