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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mili
    -0.07
    reation
    -0.07
    licence
    -0.07
    .metroLabel
    -0.07
    .getWindow
    -0.06
     insistence
    -0.06
    Create
    -0.06
    =-=-=-=-=-=-=-=-
    -0.06
    -download
    -0.06
     как
    -0.06
    POSITIVE LOGITS
    ης
    0.07
     �
    0.07
     виход
    0.07
     رسانه
    0.06
    ointments
    0.06
     همه
    0.06
     NOTE
    0.06
    egasus
    0.06
     woodworking
    0.06
     Derrick
    0.06
    Act Density 0.001%

    No Known Activations