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

    Neuronpedia

    INDEX
    Explanations

    code or references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geopol
    -0.07
    	fp
    -0.06
    �
    -0.06
     갤
    -0.06
     Bras
    -0.06
     врем
    -0.06
    (where
    -0.06
     сни
    -0.06
     يت
    -0.06
     bý
    -0.06
    POSITIVE LOGITS
    ême
    0.07
    upert
    0.07
    %;
    0.07
     udál
    0.07
     COMPANY
    0.07
    	protected
    0.06
     Micro
    0.06
    unless
    0.06
     Trainer
    0.06
    佳
    0.06
    Act Density 0.000%

    No Known Activations