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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Traditional
    -0.07
    alendar
    -0.06
     talks
    -0.06
    '^
    -0.06
    -0.06
    Contracts
    -0.06
     revert
    -0.06
     lectures
    -0.06
     owing
    -0.06
    には
    -0.06
    POSITIVE LOGITS
     prostřednictvím
    0.08
     통해
    0.08
     cestu
    0.08
    Through
    0.07
     through
    0.07
     Through
    0.07
     insider
    0.07
     endregion
    0.07
    一緒
    0.07
     kterém
    0.06
    Act Density 0.040%

    No Known Activations