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

    Neuronpedia

    INDEX
    Explanations

    Code with Russian Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    251
    -0.07
     DFA
    -0.07
     CPU
    -0.06
     Ná
    -0.06
     sweet
    -0.06
    -neutral
    -0.06
     Duc
    -0.06
    仲
    -0.06
     Capture
    -0.06
    Credential
    -0.06
    POSITIVE LOGITS
    .popup
    0.07
     seperti
    0.07
    Listening
    0.06
    @implementation
    0.06
    interface
    0.06
    foreign
    0.06
    .package
    0.06
    ELCOME
    0.06
     kıs
    0.06
    верж
    0.06
    Act Density 0.002%

    No Known Activations