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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quoting
    -0.07
     utterly
    -0.07
     OTHER
    -0.07
     archae
    -0.07
     deutschland
    -0.06
    charges
    -0.06
     Kern
    -0.06
    _tot
    -0.06
     drifted
    -0.06
     intercourse
    -0.06
    POSITIVE LOGITS
    opot
    0.06
    .Security
    0.06
    resolver
    0.06
    sending
    0.06
     smr
    0.06
    .vocab
    0.06
     tập
    0.06
    Finder
    0.06
    .reloadData
    0.06
     sendMessage
    0.06
    Act Density 0.000%

    No Known Activations