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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     edema
    0.85
     alkaloids
    0.85
    🙎
    0.84
     excreted
    0.84
     computeEncoder
    0.82
     orbits
    0.81
     antitumor
    0.81
     enteros
    0.80
     biases
    0.80
     orbitals
    0.80
    POSITIVE LOGITS
    Con
    1.12
    Bar
    0.94
    J
    0.93
    c
    0.93
    BC
    0.92
    OP
    0.91
    AC
    0.90
    A
    0.90
    b
    0.89
    con
    0.88
    Act Density 0.000%

    No Known Activations