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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     selfless
    0.79
    opuerto
    0.78
     között
    0.76
     ganze
    0.74
     Saleh
    0.73
     rzecz
    0.73
     nguyện
    0.72
     Opens
    0.71
     ignited
    0.71
     wśród
    0.71
    POSITIVE LOGITS
    s
    0.98
    Lionel
    0.84
    CAM
    0.81
    SPC
    0.80
    ات
    0.78
    Mrs
    0.78
    Campbell
    0.77
    Classifier
    0.77
    Marc
    0.77
    BOSTON
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.