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

    Neuronpedia

    INDEX
    Explanations

    knockout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iful
    -0.07
     Occupy
    -0.07
     Zack
    -0.07
    もない
    -0.06
    sak
    -0.06
     Sak
    -0.06
     Raqqa
    -0.06
     iCloud
    -0.06
    ذي
    -0.06
    ﻴ
    -0.06
    POSITIVE LOGITS
    shutdown
    0.07
     comparative
    0.07
     uplifting
    0.07
     manifestation
    0.06
    _most
    0.06
     killings
    0.06
     formal
    0.06
     Relationships
    0.06
     msg
    0.06
     shutdown
    0.06
    Act Density 0.001%

    No Known Activations