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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <unused21>
    0.86
    átku
    0.77
     localizada
    0.77
     selfishness
    0.76
     था
    0.75
    smouth
    0.75
    โก
    0.74
    терна
    0.74
    blower
    0.74
    <unused92>
    0.73
    POSITIVE LOGITS
     High
    0.74
    0.71
     Quincy
    0.70
     this
    0.69
     Zhejiang
    0.69
     Napoli
    0.66
     ovarian
    0.66
    𖤐
    0.65
     passwd
    0.64
     clog
    0.63
    Act Density 0.000%

    No Known Activations