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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arbit
    0.88
    なんと
    0.86
    ch
    0.83
    🦆
    0.81
    یت
    0.79
    𝗵
    0.78
    ándolo
    0.77
    baden
    0.77
    لوك
    0.77
    cr
    0.76
    POSITIVE LOGITS
    Forge
    1.00
     Dabei
    0.97
    શ્મી
    0.97
     remarks
    0.95
    ल्फ
    0.94
     automorphisms
    0.94
     blueprints
    0.93
     locomotives
    0.93
     forth
    0.93
    ಲ್ಲು
    0.93
    Act Density 0.000%

    No Known Activations