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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YN
    -0.07
    ैत
    -0.07
     onion
    -0.07
     Το
    -0.07
     RANGE
    -0.07
    zek
    -0.07
     AVG
    -0.07
    ynos
    -0.07
     hatred
    -0.06
     Plates
    -0.06
    POSITIVE LOGITS
    ühl
    0.07
    AXB
    0.06
     pursuing
    0.06
    0.06
    0.06
    bilir
    0.06
    ывал
    0.06
     blowjob
    0.06
     (<
    0.06
     robotics
    0.06
    Act Density 0.000%

    No Known Activations