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

    Neuronpedia

    INDEX
    Explanations

    business and technical

    np_max-act · gemini-2.0-flash

    The neuron responds to words describing user‐interface or aesthetic software qualities (e.g., “appearance”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Day
    -0.08
    _putchar
    -0.07
    REFIX
    -0.07
     sodium
    -0.06
    .coordinate
    -0.06
    (coords
    -0.06
    .STATE
    -0.06
    	address
    -0.06
    Against
    -0.06
     Latitude
    -0.06
    POSITIVE LOGITS
     orig
    0.07
     masturb
    0.06
     Mö
    0.06
     кг
    0.06
    precio
    0.06
    hythm
    0.06
     leh
    0.06
    曾
    0.06
     deposit
    0.06
     Shoes
    0.06
    Act Density 0.176%

    No Known Activations