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

    Neuronpedia

    INDEX
    Explanations

    ib

    np_max-act · gemini-2.0-flash

    The neuron is activated by Portuguese-language words or word‐pieces, so it detects Portuguese text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    |.
    -0.07
    afd
    -0.07
    .;.;
    -0.06
     nine
    -0.06
    modification
    -0.06
    instanc
    -0.06
    ие
    -0.06
     strpos
    -0.06
     rectangles
    -0.06
     ADA
    -0.06
    POSITIVE LOGITS
     sidew
    0.07
    William
    0.06
     subdivisions
    0.06
    �
    0.06
    .setParameter
    0.06
     밤
    0.06
    .LayoutParams
    0.06
     Wor
    0.06
     допом
    0.06
     sporting
    0.06
    Act Density 0.583%

    No Known Activations