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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Well
    -0.07
    83
    -0.06
    Sean
    -0.06
    cych
    -0.06
    “At
    -0.06
     �
    -0.06
     branching
    -0.06
     isp
    -0.06
     Щ
    -0.06
    "At
    -0.06
    POSITIVE LOGITS
    _iv
    0.07
     applies
    0.07
     inflater
    0.07
     instantiated
    0.07
    ы
    0.06
    +-+-+-+-+-+-+-+-
    0.06
    ISE
    0.06
    (""+
    0.06
     Enc
    0.06
     reclaimed
    0.06
    Act Density 0.004%

    No Known Activations