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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    813
    -0.07
    AQ
    -0.07
    alardan
    -0.07
     evalu
    -0.07
    Planning
    -0.07
    Depending
    -0.07
    ctica
    -0.07
     açısından
    -0.06
     yıllık
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
    권
    0.06
    )c
    0.06
    OUS
    0.06
    طاق
    0.06
     Microsystems
    0.06
    ioned
    0.06
     disrupt
    0.06
    friend
    0.06
    pellier
    0.06
    覆
    0.06
    Act Density 0.055%

    No Known Activations