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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash

    This neuron responds to inline mathematical symbols or formula variables (e.g. single-letter variables in LaTeX/math mode).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    \a
    -0.06
     Naughty
    -0.06
    reu
    -0.06
     رو
    -0.06
     
    -0.06
    ustr
    -0.06
    敷
    -0.06
     glossy
    -0.06
    ilor
    -0.06
     اختیار
    -0.06
    POSITIVE LOGITS
     marry
    0.08
    .Results
    0.07
     สพป
    0.07
    .hasMore
    0.07
    coma
    0.06
    ,’”
    0.06
     Qui
    0.06
    ]));
    0.06
    .toggle
    0.06
     teammates
    0.06
    Act Density 0.032%

    No Known Activations