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

    Neuronpedia

    INDEX
    Explanations

    conclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dol
    -0.07
     MatTable
    -0.07
    uyor
    -0.07
     jeho
    -0.06
     adrenaline
    -0.06
     policy
    -0.06
    makt
    -0.06
     små
    -0.06
     concurrent
    -0.06
     Evil
    -0.06
    POSITIVE LOGITS
    íše
    0.07
     حديث
    0.07
    �
    0.07
    钢
    0.06
     бач
    0.06
     cooling
    0.06
     와
    0.06
     SYMBOL
    0.06
    ()},↵
    0.06
    ΙΣ
    0.06
    Act Density 0.004%

    No Known Activations