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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Belgium
    0.50
     å
    0.50
    Germany
    0.49
     germany
    0.47
    France
    0.47
     Hungary
    0.46
    Hungary
    0.46
     zu
    0.45
     c
    0.45
     Africa
    0.44
    POSITIVE LOGITS
    rzy
    0.39
     ня
    0.38
     inwards
    0.37
     shutdowns
    0.36
     interruptions
    0.35
    重大
    0.35
     fonction
    0.34
     अर्थ
    0.34
    муля
    0.34
    זר
    0.34
    Act Density 0.000%

    No Known Activations