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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ับปร
    -0.07
    Processing
    -0.07
     IKE
    -0.07
     topology
    -0.07
     Decl
    -0.06
    替
    -0.06
    ortal
    -0.06
     bufferSize
    -0.06
    ôte
    -0.06
    研究
    -0.06
    POSITIVE LOGITS
    .PUT
    0.07
    scalar
    0.06
    .Disclaimer
    0.06
    ses
    0.06
    compet
    0.06
    .:
    0.06
    еліг
    0.06
     intoxic
    0.06
    "]))
    0.06
     داشته
    0.06
    Act Density 0.046%

    No Known Activations