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

    Neuronpedia

    INDEX
    Explanations

    html code related to tables and lists

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.62
     تضيفلها
    -0.59
    labelledby
    -0.59
    iture
    -0.55
    IContainer
    -0.54
     وتسجيلات
    -0.53
    Personensuche
    -0.52
    Filmographie
    -0.51
    donate
    -0.50
    etragen
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.54
    
    0.53
     bő
    0.53
    uxxxx
    0.52
    }))
    0.52
     chronique
    0.51
    cluye
    0.50
     nôtre
    0.49
    farwyddwr
    0.49
     Ciao
    0.49
    Act Density 0.280%

    No Known Activations