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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hoh
    0.58
    ➌
    0.57
    "]')
    0.57
     EDL
    0.57
     ISZ
    0.55
    txtbtn
    0.52
    ⇣
    0.52
     nanocom
    0.52
    ទ្
    0.50
     ++)
    0.50
    POSITIVE LOGITS
    Bailey
    0.55
     Bailey
    0.52
     Kirk
    0.49
    Kirk
    0.47
    ↵
    0.46
    it
    0.45
    ike
    0.45
    ik
    0.44
    idge
    0.41
    Глав
    0.41
    Act Density 0.000%

    No Known Activations