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

    Neuronpedia

    INDEX
    Explanations

    mains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الی
    -0.07
    070
    -0.06
     phrases
    -0.06
    ariance
    -0.06
    listed
    -0.06
     Lab
    -0.06
    _prefix
    -0.06
    ties
    -0.06
    럽
    -0.06
    	table
    -0.06
    POSITIVE LOGITS
     kay
    0.07
     Reyn
    0.06
     dwell
    0.06
    LocalizedString
    0.06
     inconvenient
    0.06
    095
    0.06
    .Cryptography
    0.06
    CELER
    0.06
    acion
    0.06
     annoyance
    0.05
    Act Density 0.011%

    No Known Activations