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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases that emphasize agreement or correlation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administr
    -0.38
     justement
    -0.38
    ngdoc
    -0.37
     calendriers
    -0.37
    ⚧
    -0.36
     Ohl
    -0.36
     spéc
    -0.36
     épu
    -0.35
    ciaż
    -0.35
     Aktiv
    -0.35
    POSITIVE LOGITS
    fjspx
    0.48
     ChromeDriver
    0.46
     jScrollPane
    0.45
    TemporalType
    0.43
    Jereo
    0.42
     εφ
    0.41
    Hozzáférés
    0.40
     препратки
    0.40
     iprot
    0.40
    RegressionTest
    0.40
    Act Density 0.055%

    No Known Activations