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

    Neuronpedia

    INDEX
    Explanations

    subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gron
    -0.07
     dés
    -0.07
    ANK
    -0.07
    _As
    -0.07
     phosphate
    -0.07
     benchmark
    -0.06
     اسپ
    -0.06
    Ar
    -0.06
     Pre
    -0.06
     displaced
    -0.06
    POSITIVE LOGITS
    bill
    0.07
     hebt
    0.07
    根本
    0.06
     Subject
    0.06
    ΗΤ
    0.06
    	mutex
    0.06
     영화
    0.06
    �
    0.06
     Όμιλος
    0.06
    を見
    0.06
    Act Density 0.001%

    No Known Activations