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

    Neuronpedia

    INDEX
    Explanations

    err

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fore
    -0.07
     inde
    -0.07
    grupo
    -0.06
    InitialState
    -0.06
     transparency
    -0.06
     valves
    -0.06
    �
    -0.06
     acceptance
    -0.06
     lý
    -0.06
     furthermore
    -0.06
    POSITIVE LOGITS
    err
    0.38
    ERR
    0.27
     Merr
    0.18
     Perr
    0.18
     Kerr
    0.18
     verr
    0.17
     Gerr
    0.17
     Herr
    0.16
    errar
    0.13
    erra
    0.13
    Act Density 0.005%

    No Known Activations