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

    Neuronpedia

    INDEX
    Explanations

    text from bug reports

    oai_token-act-pair · gemini-2.0-flash

    tickets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.16
    saraba
    -0.84
     autorytatywna
    -0.78
    SequentialGroup
    -0.78
     Baillargeon
    -0.74
     متحده
    -0.74
    Controllo
    -0.72
    AddHtmlAttribute
    -0.70
     '\\;'
    -0.68
    󠁢
    -0.68
    POSITIVE LOGITS
     tickets
    0.73
     fermés
    0.69
     Ticket
    0.69
     closed
    0.69
     ticket
    0.68
     Tickets
    0.68
     closing
    0.68
    Ticket
    0.65
    ticket
    0.65
    Tickets
    0.64
    Act Density 1.331%

    No Known Activations