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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Virgin
    -0.08
    	message
    -0.07
    .Resources
    -0.07
    As
    -0.07
     strncmp
    -0.07
    晨
    -0.07
     Removing
    -0.07
    sendMessage
    -0.07
    不存在
    -0.07
     André
    -0.07
    POSITIVE LOGITS
     HOR
    0.07
    ギャ
    0.07
    Ӂ
    0.07
     Hollywood
    0.06
     voltage
    0.06
    affiliate
    0.06
    мож
    0.06
     leur
    0.06
     직
    0.06
     nephew
    0.06
    Act Density 0.010%

    No Known Activations