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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of experimental control conditions, especially “negative control” and “positive control.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hotmail
    -0.07
     pelos
    -0.06
    itone
    -0.06
     повідом
    -0.06
    επ
    -0.06
     cita
    -0.06
     gluc
    -0.06
    jad
    -0.06
     Mediterr
    -0.06
     isso
    -0.05
    POSITIVE LOGITS
    	read
    0.07
     model
    0.06
     Should
    0.06
     Donald
    0.06
     pokrač
    0.06
    !important
    0.06
    (;
    0.06
     upscale
    0.06
    σταση
    0.06
    	lcd
    0.06
    Act Density 0.005%

    No Known Activations