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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cartoon
    -0.08
    Mine
    -0.08
    🤱
    -0.07
    .navigate
    -0.07
    }-
    -0.07
    }]
    -0.07
     bombings
    -0.07
     reserved
    -0.06
    ()};↵
    -0.06
     onCreateViewHolder
    -0.06
    POSITIVE LOGITS
    roe
    0.08
     Cage
    0.07
    lük
    0.07
     noon
    0.07
    URN
    0.07
    coder
    0.07
    aptops
    0.06
     glob
    0.06
     Forty
    0.06
    allis
    0.06
    Act Density 0.061%

    No Known Activations