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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getClass
    -0.07
     details
    -0.07
    cred
    -0.07
    td
    -0.07
    𝒍
    -0.07
    cherche
    -0.06
     pr
    -0.06
     ),
    -0.06
    	im
    -0.06
     –
    -0.06
    POSITIVE LOGITS
    골
    0.07
    \Configuration
    0.07
    俄军
    0.07
    _GPIO
    0.07
    olson
    0.06
    昴
    0.06
     Orthodox
    0.06
    裔
    0.06
    Cars
    0.06
    ouv
    0.06
    Act Density 0.003%

    No Known Activations