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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional distress or uncertainty

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

    Japanese language fragments

    np_acts-logits-general · gemini-2.0-flash

    よし うん ちょっと

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )");
    -0.56
    "{\
    -0.56
    ()");
    -0.56
    "})
    -0.55
     ?>
    -0.54
     "'");
    -0.52
     smtplib
    -0.52
    //}
    -0.51
    !")
    -0.51
     Formosa
    -0.50
    POSITIVE LOGITS
     somehow
    0.61
    itattu
    0.57
    WebServlet
    0.54
    providedIn
    0.54
     InputDecoration
    0.53
     Manusia
    0.53
     Somehow
    0.52
     even
    0.52
     Contrary
    0.51
     sakit
    0.51
    Act Density 0.098%

    No Known Activations