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

    Neuronpedia

    INDEX
    Explanations

    traffic lights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Myers
    -0.08
     notebooks
    -0.08
     Flynn
    -0.08
     Mig
    -0.08
     Middleware
    -0.08
     provenance
    -0.07
     intellectual
    -0.07
     memoir
    -0.07
     Notebook
    -0.07
    .spotify
    -0.07
    POSITIVE LOGITS
     cycling
    0.09
    _rotation
    0.09
     дл
    0.08
    周期
    0.08
     intemp
    0.08
    _lengths
    0.08
     Cycling
    0.08
    _cycle
    0.08
     overgang
    0.08
     uitleg
    0.08
    Act Density 0.004%

    No Known Activations