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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation in scientific or technical contexts

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

    closing punctuation, math, citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </u>
    -0.61
    </i>
    -0.59
    </b>
    -0.58
    </strong>
    -0.54
    IntoConstraints
    -0.52
    </em>
    -0.51
    </h3>
    -0.50
    RTEE
    -0.50
    Sucesor
    -0.48
    }{*}{
    -0.48
    POSITIVE LOGITS
    )))),
    0.40
    ]])
    0.39
    }}}}
    0.39
     pregunto
    0.38
    berdayakan
    0.36
    })),
    0.35
    harapkan
    0.35
    ])),
    0.35
    \{\\
    0.34
    yorsunuz
    0.34
    Act Density 0.794%

    No Known Activations