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

    Neuronpedia

    INDEX
    Explanations

    Apache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triệu
    -0.07
    �
    -0.07
    Array
    -0.07
    очно
    -0.07
    .selector
    -0.06
     ко
    -0.06
     �
    -0.06
    	include
    -0.06
     pInfo
    -0.06
     Sword
    -0.06
    POSITIVE LOGITS
     edilen
    0.07
     "}↵
    0.07
    Convention
    0.06
    ~↵
    0.06
    -build
    0.06
    egie
    0.06
    reetings
    0.06
     pounds
    0.06
     recommendation
    0.06
     miles
    0.06
    Act Density 0.003%

    No Known Activations