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

    Neuronpedia

    INDEX
    Explanations

    times when something negative is stated, and then followed by disagreement

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    раздо
    -0.53
    unzel
    -0.50
     للمعارف
    -0.49
     tiens
    -0.49
     judiciales
    -0.49
    ioneta
    -0.47
    crumbs
    -0.46
    Nevertheless
    -0.46
    ույ
    -0.46
     dangere
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.73
     Roskov
    0.72
     disambiguazione
    0.66
    SpringRunner
    0.66
    RegressionTest
    0.63
    WebControls
    0.60
    WriteTagHelper
    0.60
    曖昧さ回避
    0.59
     Taktlose
    0.58
    Personensuche
    0.57
    Act Density 0.065%

    No Known Activations