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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etet
    0.75
    anso
    0.75
    ast
    0.74
    abs
    0.73
    ap
    0.72
    3
    0.72
    1
    0.70
     జ
    0.70
    absorption
    0.70
    あって
    0.70
    POSITIVE LOGITS
     occidental
    0.81
     clumsy
    0.80
    '
    0.79
    }+(
    0.76
     evolve
    0.75
     trampled
    0.70
    Académie
    0.70
    ික
    0.69
    Nella
    0.69
     heartwarming
    0.69
    Act Density 0.000%

    No Known Activations