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

    Neuronpedia

    INDEX
    Explanations

    Helsinki

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annual
    -0.07
    관계
    -0.06
     BUFFER
    -0.06
     originates
    -0.06
     descriptive
    -0.06
     Social
    -0.06
    -piece
    -0.06
     ballot
    -0.06
    анні
    -0.06
     Peng
    -0.06
    POSITIVE LOGITS
    ्त
    0.07
    itty
    0.07
    .tem
    0.06
    ertino
    0.06
     broccoli
    0.06
    UIAlertView
    0.06
     ticari
    0.06
    %^
    0.06
     Discord
    0.06
     LoginComponent
    0.06
    Act Density 0.001%

    No Known Activations