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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    it
    0.92
    orn
    0.77
    莎
    0.76
    裡
    0.75
    atr
    0.75
    lab
    0.73
    its
    0.73
    raw
    0.72
    hir
    0.71
    どのような
    0.71
    POSITIVE LOGITS
    Noeud
    0.76
     почвы
    0.69
     arabe
    0.66
    よび
    0.66
    вающие
    0.65
    ៧
    0.64
    UserProfile
    0.64
    0.63
     препарата
    0.63
     canh
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.