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

    Neuronpedia

    INDEX
    Explanations

    Focus on specific actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ociety
    0.54
     epidemiology
    0.50
    iatrics
    0.47
    citizens
    0.47
     یورپی
    0.45
     extranj
    0.44
    social
    0.43
     taxpayers
    0.43
     internazionale
    0.42
    irting
    0.42
    POSITIVE LOGITS
    LE
    0.46
    ඡ
    0.46
     ПК
    0.45
    Constr
    0.44
    ല്‍
    0.44
     नक्सलियों
    0.44
    FIFO
    0.43
    产生的
    0.42
    AspectRatio
    0.42
     Minecraft
    0.42
    Act Density 0.005%

    No Known Activations