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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ud
    -0.07
     negotiation
    -0.06
     vault
    -0.06
    anonymous
    -0.06
     mim
    -0.06
    よりも
    -0.06
     Vault
    -0.06
    .Topic
    -0.06
     ineligible
    -0.06
     роки
    -0.06
    POSITIVE LOGITS
     Vive
    0.07
     grateful
    0.06
    exels
    0.06
    №
    0.06
     Mata
    0.06
    estruction
    0.06
    нему
    0.06
    ersonic
    0.06
    uvre
    0.06
     Федера
    0.06
    Act Density 0.002%

    No Known Activations