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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surely
    -0.07
     sign
    -0.07
    956
    -0.07
    -st
    -0.07
     id
    -0.06
     kok
    -0.06
    �
    -0.06
    RPC
    -0.06
     unab
    -0.06
     realistic
    -0.06
    POSITIVE LOGITS
    ║
    0.06
     udál
    0.06
     Carmen
    0.06
    ]|[
    0.06
    _exe
    0.06
    .MONTH
    0.06
    にて
    0.06
    .Files
    0.06
     _↵↵
    0.06
    ServiceProvider
    0.06
    Act Density 0.039%

    No Known Activations