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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     measurement
    0.74
    measurable
    0.66
    观测
    0.64
     measurements
    0.64
    measurement
    0.64
     disorientation
    0.62
    centage
    0.62
    ㅓ
    0.62
    证据
    0.61
    udrait
    0.58
    POSITIVE LOGITS
     raconte
    0.63
     Amplify
    0.61
     Unlock
    0.60
     aplicativos
    0.60
    באנגלית
    0.59
    こうした
    0.59
     рассказыва
    0.59
     Großbritannien
    0.59
     sederhana
    0.59
     installers
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.