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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _step
    -0.07
    ião
    -0.06
     jejichž
    -0.06
     pareja
    -0.06
     tercer
    -0.06
    uerdo
    -0.06
     idiots
    -0.06
     crab
    -0.06
    __':↵
    -0.06
     مع
    -0.06
    POSITIVE LOGITS
    ervative
    0.07
    ेहर
    0.07
    "id
    0.07
    assis
    0.06
     Slack
    0.06
    	printk
    0.06
    _slot
    0.06
     liên
    0.06
     शर
    0.06
     Zag
    0.06
    Act Density 0.000%

    No Known Activations