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

    Neuronpedia

    INDEX
    Explanations

    Mentorship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toured
    -0.09
     resulted
    -0.09
     Roofing
    -0.09
     depot
    -0.08
    /preferences
    -0.08
     conveyor
    -0.08
     alternatively
    -0.08
     totaled
    -0.08
     rezult
    -0.08
    ulam
    -0.08
    POSITIVE LOGITS
     aspiring
    0.11
    �
    0.09
    提高
    0.09
     yngre
    0.09
    新人
    0.09
     younger
    0.09
     संघर्ष
    0.08
    Base
    0.08
     молод
    0.08
    DTO
    0.08
    Act Density 0.096%

    No Known Activations