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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    profiles
    -0.06
     tips
    -0.06
    Swift
    -0.06
     dbHelper
    -0.06
    _CP
    -0.06
    appoint
    -0.06
    (".")
    -0.06
    bullet
    -0.06
    XMLElement
    -0.06
    措施
    -0.06
    POSITIVE LOGITS
     moto
    0.07
    _nonce
    0.07
     mutations
    0.07
     panda
    0.06
     Disease
    0.06
    _um
    0.06
    acted
    0.06
     disrupting
    0.06
     succesfully
    0.06
     Muhammad
    0.06
    Act Density 0.000%

    No Known Activations