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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     十
    -0.07
     Forever
    -0.07
    休
    -0.07
     Auschwitz
    -0.06
    	fields
    -0.06
    ices
    -0.06
    .Valid
    -0.06
    иб
    -0.06
    "urls
    -0.06
     Aging
    -0.06
    POSITIVE LOGITS
     состоит
    0.07
    Arthur
    0.07
    Messenger
    0.06
     δημο
    0.06
    gst
    0.06
     ㅇ
    0.06
     Cour
    0.06
     feels
    0.06
     wizard
    0.06
    хови
    0.06
    Act Density 0.024%

    No Known Activations