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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbers followed by a plural noun

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfans
    -0.63
     avoient
    -0.59
     vícti
    -0.59
     virtuales
    -0.57
     dieux
    -0.57
     varandra
    -0.56
     appartiennent
    -0.56
     supérieurs
    -0.56
     étoient
    -0.56
     rispar
    -0.54
    POSITIVE LOGITS
    akterysty
    0.57
     RouterModule
    0.57
    cahontas
    0.56
    genstein
    0.56
     light
    0.55
    styleUrls
    0.54
    kheim
    0.54
    rxjs
    0.53
     radical
    0.52
    Damit
    0.52
    Act Density 1.794%

    No Known Activations