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

    Neuronpedia

    INDEX
    Explanations

    relatively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fun
    -0.08
     Austin
    -0.07
     wasted
    -0.07
     bas
    -0.07
    DED
    -0.07
     done
    -0.07
     Dawn
    -0.07
     song
    -0.07
     frightened
    -0.07
    AWN
    -0.07
    POSITIVE LOGITS
     relatively
    0.19
    .Event
    0.07
     comparatively
    0.07
     responseType
    0.07
     sorun
    0.06
    阿
    0.06
    ační
    0.06
    (records
    0.06
    ãeste
    0.06
    較
    0.06
    Act Density 0.007%

    No Known Activations