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

    Neuronpedia

    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Were
    -0.07
    觉
    -0.07
    -Javadoc
    -0.07
     fear
    -0.06
     feet
    -0.06
     fees
    -0.06
     Nord
    -0.06
    158
    -0.06
     Çok
    -0.06
     know
    -0.06
    POSITIVE LOGITS
    "/>
↵
    0.07
     đạo
    0.06
    ละคร
    0.06
    	MPI
    0.06
     Cass
    0.06
    ...↵↵↵↵
    0.06
    })();↵↵
    0.06
    στημα
    0.06
    .Mapping
    0.06
     mastering
    0.06
    Act Density 0.011%

    No Known Activations