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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hattam
    0.54
    迲
    0.54
    洊
    0.54
    柾
    0.52
    ။
    0.52
    㡱
    0.51
    registrer
    0.51
    ၊
    0.51
    <unused1008>
    0.51
    நிலைய
    0.50
    POSITIVE LOGITS
    0.50
     go
    0.48
     end
    0.46
     supports
    0.46
     a
    0.45
     all
    0.45
     canceled
    0.45
     declines
    0.45
     hosts
    0.45
     forward
    0.43
    Act Density 0.003%

    No Known Activations