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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lights
    -0.08
     Magdalena
    -0.08
     Partnerships
    -0.08
     दक्ष
    -0.08
     Recommendations
    -0.08
    angka
    -0.08
     टिप्पणी
    -0.08
     excav
    -0.08
     Diario
    -0.07
     टिप्प
    -0.07
    POSITIVE LOGITS
    রাস
    0.08
     exist
    0.08
    จริง
    0.08
    েবা
    0.08
     invention
    0.08
    Exist
    0.07
     existence
    0.07
    Second
    0.07
     현실
    0.07
     gripe
    0.07
    Act Density 0.012%

    No Known Activations