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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faſt
    -0.64
    tonsoft
    -0.57
     ſmall
    -0.54
     houſe
    -0.53
    stones
    -0.51
    fır
    -0.51
     facie
    -0.51
    horesis
    -0.51
     Song
    -0.50
     stables
    -0.49
    POSITIVE LOGITS
    millan
    0.55
    bling
    0.54
    bled
    0.52
    GoogleApiClient
    0.50
    ble
    0.49
     municipales
    0.48
    parsedMessage
    0.46
    belec
    0.46
     MEASURES
    0.46
    HtmlAttribute
    0.46
    Act Density 0.002%

    No Known Activations