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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Predicate
    -0.07
    	c
    -0.07
     realised
    -0.07
     subsidiary
    -0.07
     Click
    -0.06
     Range
    -0.06
     Steps
    -0.06
     Forgotten
    -0.06
    톤
    -0.06
    kim
    -0.06
    POSITIVE LOGITS
    azon
    0.06
     lasc
    0.06
     explo
    0.06
    drm
    0.06
     چاپ
    0.06
    att
    0.06
     desea
    0.06
     metab
    0.06
     лес
    0.06
    ัป
    0.06
    Act Density 0.122%

    No Known Activations