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

    Neuronpedia

    INDEX
    Explanations

    Least Concern listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dành
    -0.07
     základ
    -0.07
    충
    -0.07
    Unary
    -0.07
     Box
    -0.06
     fik
    -0.06
     ordinarily
    -0.06
    �
    -0.06
     Becker
    -0.06
     Си
    -0.06
    POSITIVE LOGITS
    NU
    0.06
     tink
    0.06
     novembre
    0.06
    秀
    0.06
     Isle
    0.06
    etc
    0.06
    юн
    0.06
     simplex
    0.06
     nuis
    0.05
     TV
    0.05
    Act Density 0.006%

    No Known Activations