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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eine
    -0.07
     könnte
    -0.07
    	context
    -0.07
    엇
    -0.06
    	gl
    -0.06
     /*
↵
    -0.06
     cosa
    -0.06
     En
    -0.06
     refactor
    -0.06
     enf
    -0.06
    POSITIVE LOGITS
    Vectors
    0.07
    レット
    0.06
     побач
    0.06
    ắ
    0.06
     Upper
    0.06
     Wilmington
    0.06
     importantly
    0.06
    ضافة
    0.06
     플레이
    0.06
    افع
    0.06
    Act Density 0.009%

    No Known Activations