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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pubb
    -0.08
    ustum
    -0.07
    severity
    -0.07
     Asians
    -0.07
     house
    -0.07
    noop
    -0.06
     kredi
    -0.06
    Si
    -0.06
     PVC
    -0.06
     cornerback
    -0.06
    POSITIVE LOGITS
    111
    0.06
     INA
    0.06
     Mé
    0.06
    Exceptions
    0.06
    _story
    0.06
    .getM
    0.06
     headers
    0.06
    ým
    0.06
    relevant
    0.06
    VertexAttribArray
    0.06
    Act Density 0.025%

    No Known Activations