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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLEAR
    -0.06
    ERO
    -0.06
    	On
    -0.06
     �
    -0.06
    	txt
    -0.06
    _OF
    -0.06
    	base
    -0.06
    MAS
    -0.06
    goto
    -0.06
    发出
    -0.05
    POSITIVE LOGITS
     Reve
    0.07
     إذا
    0.07
     karşılık
    0.07
     직접
    0.07
     humid
    0.07
     thể
    0.06
     کنید
    0.06
    \E
    0.06
     ​​​
    0.06
     biểu
    0.06
    Act Density 0.009%

    No Known Activations