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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to gaining popularity or success

    oai_token-act-pair · gemini-2.0-flash

    gaining popularity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.72
     initComponents
    -0.65
     AssemblyCompany
    -0.62
    ftagPool
    -0.61
     الحره
    -0.61
    RegressionTest
    -0.60
    HtmlAttribute
    -0.58
    __*/
    -0.58
     devenus
    -0.54
    ChildIndex
    -0.54
    POSITIVE LOGITS
    komme
    0.51
    aş
    0.50
    дыду
    0.47
    ✨:
    0.47
    ế
    0.43
    oncesto
    0.41
     Bathing
    0.41
    很大
    0.41
    BRE
    0.41
    Lauf
    0.41
    Act Density 0.625%

    No Known Activations