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

    Neuronpedia

    INDEX
    Explanations

    Scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    渡
    -0.07
    .species
    -0.07
     중요한
    -0.07
    ochastic
    -0.06
    了解
    -0.06
     INLINE
    -0.06
     분류
    -0.06
    arcer
    -0.06
    스코
    -0.06
     теперь
    -0.06
    POSITIVE LOGITS
     dart
    0.07
    GM
    0.06
    ор
    0.06
     HIS
    0.06
     ↵
    0.06
    %)↵
    0.06
    	fprintf
    0.06
    .dirty
    0.06
    �
    0.06
    	init
    0.06
    Act Density 0.082%

    No Known Activations