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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爵
    -0.07
    än
    -0.06
    	UFUNCTION
    -0.06
     Cad
    -0.06
     MUST
    -0.06
    _CAM
    -0.06
     Buf
    -0.06
    \Bundle
    -0.06
    /OR
    -0.06
     preached
    -0.05
    POSITIVE LOGITS
    ese
    0.07
    кова
    0.07
    ilm
    0.07
    916
    0.07
     stressing
    0.07
    iles
    0.06
    ik
    0.06
    (view
    0.06
    291
    0.06
    aley
    0.06
    Act Density 0.000%

    No Known Activations