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

    Neuronpedia

    INDEX
    Explanations

    requests for research studies or proposals

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

    technical or formal phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liesslich
    -0.51
     '\\;'
    -0.51
     kiin
    -0.50
     ब्रेकडाउन
    -0.49
     entanto
    -0.49
    zzleHttp
    -0.49
    retanto
    -0.48
     obviamente
    -0.48
     INTERESAR
    -0.48
    Nachteile
    -0.48
    POSITIVE LOGITS
    expandindo
    0.39
     وتسجيلات
    0.36
    iented
    0.35
    Mild
    0.35
     để
    0.34
     möglichst
    0.34
    Erstellt
    0.34
    わざ
    0.34
     Bib
    0.33
     joaat
    0.33
    Act Density 0.101%

    No Known Activations