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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    顐
    0.51
    critic
    0.50
     sensibilité
    0.49
    beau
    0.49
    cmb
    0.49
    pseudo
    0.49
    editors
    0.48
    édie
    0.47
     अटेम्प्ट
    0.47
    cep
    0.47
    POSITIVE LOGITS
     ssh
    0.53
     router
    0.51
     schn
    0.50
    0.48
     mad
    0.48
    _
    0.47
    Out
    0.47
     Out
    0.46
     wooden
    0.46
     一个
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.