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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Constants
    -0.08
    (Configuration
    -0.07
    Ỏ
    -0.07
    .Host
    -0.07
    海尔
    -0.07
    上有
    -0.07
    责
    -0.07
     rust
    -0.06
     Math
    -0.06
    operator
    -0.06
    POSITIVE LOGITS
    Ph
    0.07
     сохр
    0.07
     Aval
    0.07
    Taken
    0.07
    _processed
    0.07
     Ved
    0.07
    עכשיו
    0.06
     killers
    0.06
    TOR
    0.06
    .layers
    0.06
    Act Density 0.027%

    No Known Activations