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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Third
    -0.07
    aju
    -0.07
    gett
    -0.07
     absor
    -0.07
    (rank
    -0.06
    lder
    -0.06
     turf
    -0.06
    transfer
    -0.06
     aggregated
    -0.06
    action
    -0.06
    POSITIVE LOGITS
    VERY
    0.08
     τη
    0.07
     Getting
    0.06
    _degree
    0.06
    ，全
    0.06
     NSError
    0.06
     try
    0.06
    .overlay
    0.06
    	glUniform
    0.06
    ‑
    0.06
    Act Density 0.104%

    No Known Activations