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

    Neuronpedia

    INDEX
    Explanations

    for applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     取
    -0.06
     Jade
    -0.06
    -plan
    -0.06
    ('.
    -0.06
    舌
    -0.06
    kit
    -0.06
     нев
    -0.06
     legends
    -0.06
    été
    -0.06
    inspace
    -0.06
    POSITIVE LOGITS
    hdl
    0.06
     OPS
    0.06
     deneyim
    0.06
    rollback
    0.06
    icient
    0.06
    _bs
    0.06
     inconsistency
    0.06
     İslâm
    0.06
     çık
    0.06
     بهتر
    0.06
    Act Density 0.012%

    No Known Activations