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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Aussi
    0.38
     bedroom
    0.37
     baratos
    0.34
     kebanyakan
    0.34
    Dieses
    0.33
     meskipun
    0.33
     quibusdam
    0.33
     mistakenly
    0.33
     founded
    0.32
     आयी
    0.32
    POSITIVE LOGITS
    V
    0.48
    Health
    0.41
    T
    0.40
    in
    0.38
    N
    0.38
    orthogonal
    0.38
    B
    0.37
    M
    0.37
    W
    0.36
    J
    0.36
    Act Density 0.000%

    No Known Activations