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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    recogn
    0.52
    ৮
    0.50
     magical
    0.48
     steeped
    0.48
    ramble
    0.47
     enchanted
    0.47
    riever
    0.46
    idirectional
    0.46
     consultative
    0.46
    leicht
    0.45
    POSITIVE LOGITS
     фигу
    0.44
     імені
    0.42
    żej
    0.42
     μέσω
    0.41
    𝘄
    0.41
    мя
    0.41
     pathologies
    0.41
     गैंगस्टर
    0.40
    できます
    0.40
    zą
    0.40
    Act Density 0.001%

    No Known Activations