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

    Neuronpedia

    INDEX
    Explanations

    syntax relating to legal and mathematical arguments

    oai_token-act-pair · gemini-2.0-flash

    code and related errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”]
    -1.90
    "]
    -1.76
    ."]
    -1.70
    .]
    -1.61
    }]
    -1.60
     ]
    -1.60
    ]
    -1.56
    "],
    -1.55
    }]$
    -1.51
    >]
    -1.51
    POSITIVE LOGITS
    </h3>
    0.77
    </h2>
    0.75
    DockStyle
    0.65
    </strong>
    0.58
    GraphicsUnit
    0.57
    </b>
    0.57
    تقاوى
    0.52
    новништво
    0.51
     résist
    0.50
     tayo
    0.50
    Act Density 2.038%

    No Known Activations