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

    Neuronpedia

    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adopt
    -0.07
     Dent
    -0.07
     =============================================================================↵
    -0.07
     Traits
    -0.07
     %%↵
    -0.07
    -aware
    -0.06
    устрой
    -0.06
    솜
    -0.06
     Dispatcher
    -0.06
     SND
    -0.06
    POSITIVE LOGITS
     проб
    0.07
    我说
    0.07
    ochond
    0.07
    defer
    0.07
     carrera
    0.07
    Close
    0.06
    ĥ
    0.06
     goodbye
    0.06
    teacher
    0.06
    _method
    0.06
    Act Density 0.011%

    No Known Activations