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

    Neuronpedia

    INDEX
    Explanations

    combining things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cele
    -0.08
    政
    -0.06
     AccessToken
    -0.06
     ions
    -0.06
     colormap
    -0.06
    стер
    -0.06
     airborne
    -0.06
    [result
    -0.06
     Baron
    -0.06
     ocean
    -0.06
    POSITIVE LOGITS
    会社
    0.07
     Kb
    0.07
    463
    0.06
    Notes
    0.06
    vertisement
    0.06
    niž
    0.06
    872
    0.06
     Butler
    0.06
    auth
    0.06
    .No
    0.06
    Act Density 0.075%

    No Known Activations